© 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. 22-GEMMASCOPE-RES-131K
    7. 34476
    Prev
    Next
    INDEX
    Explanations

    technical parts

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

    The neuron flags domain-specific technical component nouns (e.g. names of mechanical parts, system elements, or device modules).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    為に
    -1.25
     umgeben
    -1.25
     gröss
    -1.19
    Ｂ
    -1.18
    様な
    -1.17
    tokine
    -1.16
    )=\
    -1.13
     größer
    -1.10
     року
    -1.10
    来自
    -1.09
    POSITIVE LOGITS
    ğlık
    1.30
    後は
    1.03
     labios
    1.01
     barnet
    1.01
     اینترن
    1.00
     curar
    0.98
    るの
    0.98
     confort
    0.98
     tirs
    0.98
     スタート
    0.97
    Activations Density 0.022%

    No Known Activations