© 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. 67531
    Prev
    Next
    INDEX
    Explanations

    certification has

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

    quantized specific steps

    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
    キャリア
    0.59
    Ｒ
    0.52
    ワーク
    0.50
    コロ
    0.49
    らず
    0.48
    チップ
    0.46
    膣
    0.46
    海
    0.46
    所の
    0.45
    に行った
    0.45
    POSITIVE LOGITS
    ن
    0.54
    embed
    0.47
     AHA
    0.47
    uk
    0.45
    ipple
    0.44
     trin
    0.44
    ándola
    0.44
    uken
    0.42
     تر
    0.41
     Ties
    0.41
    Activations Density 0.000%

    No Known Activations