© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 59617
    Prev
    Next
    INDEX
    Explanations

    possessive statements and actions

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron fires on immediate repetition of the same word or phrase (e.g. “business is business,” “tagad ir tagad”) as a rhetorical or emphatic device.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    luas
    -1.16
    omores
    -1.09
    ellige
    -1.08
     spannende
    -1.05
    Peny
    -1.03
    সং
    -1.03
    ÈRE
    -1.02
     anderen
    -1.02
     interessante
    -1.01
    zahlung
    -1.01
    POSITIVE LOGITS
     without
    1.38
     stated
    1.23
    romas
    1.23
     vaguely
    1.20
     well
    1.18
    eration
    1.17
     although
    1.16
     after
    1.16
     only
    1.15
     significant
    1.14
    Activations Density 0.040%

    No Known Activations