© 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. 46170
    Prev
    Next
    INDEX
    Explanations

    tissue samples

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

    text followed by punctuation or special characters

    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
     higiene
    0.48
    אין
    0.48
     indicators
    0.46
    پیگنڈ
    0.45
    Пла
    0.44
     diminution
    0.44
    ྒ
    0.44
    йда
    0.43
     economical
    0.42
    Сма
    0.42
    POSITIVE LOGITS
    ens
    0.52
    ched
    0.51
    ent
    0.50
     Pastoral
    0.49
    of
    0.49
    is
    0.48
    h
    0.47
    was
    0.47
    ed
    0.47
    ss
    0.46
    Activations Density 0.000%

    No Known Activations