© 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. 14866
    Prev
    Next
    INDEX
    Explanations

    ending parenthesis after question

    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_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
    蟜
    -3.03
     vorigen
    -2.64
    В
    -2.33
    乄
    -2.33
     Gegensatz
    -2.33
     Changing
    -2.31
    戗
    -2.25
    薗
    -2.23
     plupart
    -2.22
    та
    -2.19
    POSITIVE LOGITS
    狁
    2.78
     şi
    2.31
     și
    2.28
    这不
    2.20
    u
    2.11
    يًا
    2.08
    粲
    2.08
    灃
    2.06
     mereka
    2.05
     cursed
    2.05
    Activations Density 0.004%

    No Known Activations