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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 110662
    Prev
    Next
    INDEX
    Explanations

    word identifiers in quotes

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     甘
    -0.63
     listed
    -0.63
    Copy
    -0.62
    lister
    -0.61
    Listed
    -0.61
    甘
    -0.60
     relatifs
    -0.60
     термо
    -0.59
     vidéo
    -0.59
    Martin
    -0.59
    POSITIVE LOGITS
     Cocktail
    0.73
    icester
    0.71
    レクト
    0.70
    Cocktail
    0.69
    :][
    0.66
     FRES
    0.65
     Nade
    0.65
     stunted
    0.65
    andes
    0.64
    的研究
    0.64
    Activations Density 0.066%

    No Known Activations