© 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. 39426
    Prev
    Next
    INDEX
    Explanations

    old harbour district

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

    breakdown and explanation

    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
    Hold
    0.46
    伤
    0.46
    쨩
    0.44
    ｚ
    0.43
    壓
    0.42
    opez
    0.41
    傷
    0.41
     Hesap
    0.41
    无数
    0.41
    ziert
    0.40
    POSITIVE LOGITS
     jargon
    0.61
     autobiography
    0.52
     d
    0.51
     quilts
    0.51
     kui
    0.50
     tabular
    0.50
     plantations
    0.49
     histogram
    0.49
     quay
    0.49
     sax
    0.48
    Activations Density 0.000%

    No Known Activations