© 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. 125053
    Prev
    Next
    INDEX
    Explanations

    shall not fear

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

    ranking people or measuring waste

    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
    خ
    0.43
     lontano
    0.43
    ᓵ
    0.41
    푅
    0.41
    ibilità
    0.40
    PubMed
    0.40
     ग्लूको
    0.40
    یکیشن
    0.40
     collinear
    0.40
    BG
    0.40
    POSITIVE LOGITS
     זי
    0.52
    </h2>
    0.49
     bearers
    0.49
    <0x0D>
    0.47
     பயன்படுத்து
    0.47
     Released
    0.46
    Operators
    0.46
     Forder
    0.46
     вулка
    0.45
     사용하는
    0.45
    Activations Density 0.001%

    No Known Activations