© 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. 78353
    Prev
    Next
    INDEX
    Explanations

    from file format

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

    compounds, entities, agent, energy, legally

    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
    co
    0.53
    níci
    0.52
    łow
    0.50
    cn
    0.48
    ow
    0.48
     ответ
    0.47
    afon
    0.46
    z
    0.46
     লেখ
    0.46
    affine
    0.46
    POSITIVE LOGITS
     Input
    0.48
    تبع
    0.44
     Warming
    0.43
     roadblock
    0.43
     BALANCE
    0.43
     DEPEND
    0.43
     trail
    0.42
    的发展
    0.42
    جاد
    0.42
     scoot
    0.42
    Activations Density 0.001%

    No Known Activations