© 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. 152209
    Prev
    Next
    INDEX
    Explanations

    your business

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

    captions, lenses, system, element, level, Person, path, indicator

    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
    i
    0.53
    Frequent
    0.51
    Архи
    0.50
     terdapat
    0.49
     marquées
    0.48
    ي
    0.48
    ᓇ
    0.48
    шил
    0.47
    Analog
    0.46
    ❰
    0.46
    POSITIVE LOGITS
     gong
    0.44
    一身
    0.44
    ands
    0.43
    STARTED
    0.43
    뵈
    0.43
     Ciebie
    0.42
    atee
    0.42
    éreo
    0.42
    essie
    0.42
    ifiable
    0.41
    Activations Density 0.000%

    No Known Activations