© 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. 199741
    Prev
    Next
    INDEX
    Explanations

    medical contexts, statistics, or product features

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

    public transport passes and cards

    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
    THAT
    0.51
    ка
    0.48
    бра
    0.46
    THE
    0.46
    GEN
    0.46
    大
    0.45
    发生了
    0.44
     determination
    0.44
    一
    0.44
    <0x80>
    0.44
    POSITIVE LOGITS
     يساعد
    0.52
    iseen
    0.50
     cinqui
    0.50
     autoimmune
    0.49
    íte
    0.49
     helpen
    0.49
     jovens
    0.48
     بچے
    0.48
     நீர்
    0.48
     périph
    0.47
    Activations Density 0.000%

    No Known Activations