© 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. 128089
    Prev
    Next
    INDEX
    Explanations

    speak louder

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

    what was once

    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
     ಹೆಸರು
    0.59
    转
    0.58
    보
    0.58
    Ft
    0.55
    бо
    0.55
     பெயர்
    0.54
    長い
    0.54
     Тран
    0.53
    Teste
    0.53
    取り付け
    0.53
    POSITIVE LOGITS
     playoffs
    0.47
     picnics
    0.46
     ci
    0.45
     reporters
    0.44
     picnic
    0.44
    ；
    0.43
     ding
    0.43
     guerrilla
    0.43
     semifinals
    0.43
     second
    0.42
    Activations Density 0.002%

    No Known Activations