© 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. 172383
    Prev
    Next
    INDEX
    Explanations

    alike, carried, succeed, alike, carried, succeed, encourage

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

    real-time capabilities and audit trail

    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
     ಹೆಸ
    0.52
    𒆕
    0.50
    からない
    0.50
    inę
    0.49
    ಕೋ
    0.48
    চি
    0.48
     Juillet
    0.48
     autographs
    0.48
    ﻤ
    0.48
    ﺒ
    0.47
    POSITIVE LOGITS
    resp
    0.48
    track
    0.46
     resp
    0.45
    the
    0.44
    arch
    0.44
     nail
    0.43
     track
    0.43
    ern
    0.43
    ä
    0.41
     Veritas
    0.41
    Activations Density 0.000%

    No Known Activations