© 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. 86134
    Prev
    Next
    INDEX
    Explanations

    repair, family, taps, elective, scripts

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

    regions space fields time

    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
    טור
    0.39
    esgue
    0.37
    युक्त
    0.36
     termed
    0.36
    ல்கள்
    0.36
    酝
    0.36
    owę
    0.35
     variously
    0.35
    <strong>
    0.35
    ondere
    0.35
    POSITIVE LOGITS
     우리가
    0.50
     परीक्षा
    0.50
     keempat
    0.46
     empê
    0.45
     όταν
    0.45
    これからも
    0.45
     aidant
    0.44
     കാരണ
    0.43
     ఉపయోగ
    0.43
     오늘도
    0.43
    Activations Density 0.002%

    No Known Activations