© 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. 196315
    Prev
    Next
    INDEX
    Explanations

    remember phrases or clauses

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

    sentiment, create, calendar, interface

    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
    )+"]
    0.48
     হাসপাতালের
    0.44
     अस्वी
    0.44
    Barrel
    0.43
    <unused2133>
    0.43
    范围
    0.43
    对其
    0.43
    Templ
    0.42
    ]*
    0.42
     తగ్గ
    0.42
    POSITIVE LOGITS
    urul
    0.52
    惣
    0.48
    ども
    0.48
    ウェブ
    0.47
    悟
    0.47
     /\
    0.46
     DAILY
    0.46
    trait
    0.46
    bloc
    0.46
    ウェイ
    0.45
    Activations Density 0.000%

    No Known Activations