© 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. 143308
    Prev
    Next
    INDEX
    Explanations

    DVD, disc, shirt, license, world peace

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

    verbs followed by 'to' or 'a'

    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
     tropos
    0.49
     seguramente
    0.49
    ăți
    0.46
     campione
    0.46
     recibió
    0.46
     nostrum
    0.45
    ᅳ
    0.45
     plena
    0.45
     dynamism
    0.43
    nPortIndex
    0.43
    POSITIVE LOGITS
     ছ
    0.45
     For
    0.43
    kA
    0.42
    ki
    0.41
    skipped
    0.41
    anska
    0.40
     লাগবে
    0.39
    Shock
    0.39
    েন্ত্র
    0.39
     sinks
    0.39
    Activations Density 0.002%

    No Known Activations