© 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. 210020
    Prev
    Next
    INDEX
    Explanations

    anything and everything

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

    plus chilling 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
    Survey
    0.47
     biomedical
    0.46
     जैव
    0.46
     개
    0.46
     Brochure
    0.46
     평
    0.46
     숙
    0.46
    eers
    0.45
    வரையும்
    0.45
     cyl
    0.44
    POSITIVE LOGITS
    一切
    0.42
    .)
    0.41
     tu
    0.39
    <0xB3>
    0.39
     nhất
    0.39
    <0x8A>
    0.38
    ことがあります
    0.38
    atani
    0.38
     executed
    0.38
    センター
    0.38
    Activations Density 0.000%

    No Known Activations