© 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. 34-GEMMASCOPE-RES-131K
    7. 79170
    Prev
    Next
    INDEX
    Explanations

    resource `Properties` `billing` `sequential` `error` `external`

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

    This neuron fires strongly on unusually long tokens (e.g. long identifiers or namespace names).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     casos
    -1.02
    )$}
    -0.94
    "';
    -0.94
    😐
    -0.93
     canales
    -0.92
     chistes
    -0.91
     familias
    -0.90
    usec
    -0.88
     Situations
    -0.87
    ursday
    -0.87
    POSITIVE LOGITS
    corns
    1.16
    ípios
    1.14
    cokinetics
    1.10
     ARISING
    1.05
    study
    1.04
     kolei
    1.03
    iguous
    1.01
    됐
    1.00
    hatta
    1.00
    бър
    0.99
    Activations Density 0.473%

    No Known Activations