© 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. 180958
    Prev
    Next
    INDEX
    Explanations

    end of project, life, or eternity

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

    "spend", "JSON"

    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
    part
    0.47
    EN
    0.45
    m
    0.45
    HDD
    0.42
    season
    0.42
    れる
    0.41
    ené
    0.41
    en
    0.40
    ക്കുന്ന
    0.40
    贫
    0.40
    POSITIVE LOGITS
     nă
    0.49
     ဆို
    0.46
     Stern
    0.45
     exercer
    0.45
     Trevelyan
    0.44
     apresentado
    0.44
     Сим
    0.44
    тацию
    0.43
     ὑ
    0.43
     shouldn
    0.43
    Activations Density 0.000%

    No Known Activations