© 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. 212505
    Prev
    Next
    INDEX
    Explanations

    code following placement

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

    industries like finance

    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
    <0x11>
    0.48
    доро
    0.48
    fasst
    0.47
     vecteur
    0.47
    வலி
    0.47
     век
    0.46
    జాగా
    0.46
    レスレット
    0.46
    ді
    0.46
    క్తి
    0.46
    POSITIVE LOGITS
    ↵↵
    0.59
    Only
    0.53
    ND
    0.52
    .
    0.50
    ive
    0.49
     baza
    0.48
     zara
    0.47
    ๆ
    0.46
     leves
    0.45
    VD
    0.45
    Activations Density 0.001%

    No Known Activations