© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 202435
    Prev
    Next
    INDEX
    Explanations

    according to statements

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

    start of new sentence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arier
    0.56
     methyl
    0.53
    ώ
    0.47
    uari
    0.46
     anthocyan
    0.46
    ெல்லி
    0.46
     meeting
    0.45
    𝙞
    0.45
     Methyl
    0.45
     cyclohexane
    0.45
    POSITIVE LOGITS
    インストール
    0.52
    K
    0.47
    データベース
    0.46
    𝚅
    0.44
    šem
    0.43
    N
    0.43
    インターネット
    0.43
     بیٹے
    0.42
    情報は
    0.41
    信息的
    0.39
    Activations Density 0.001%

    No Known Activations