© 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. 53351
    Prev
    Next
    INDEX
    Explanations

    comparison, recreation, measurement, chronic

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

    exploring current topics

    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
     cuja
    0.46
    Verdict
    0.45
     catastrophes
    0.43
     effetti
    0.42
    thememanager
    0.42
    quando
    0.42
     efeito
    0.41
    ኋ
    0.41
     effet
    0.41
    可知
    0.41
    POSITIVE LOGITS
     помощь
    0.48
    ai
    0.47
    art
    0.44
     ၁
    0.44
     मसल
    0.44
    di
    0.43
    aid
    0.43
    aring
    0.43
    apping
    0.42
    asis
    0.42
    Activations Density 0.000%

    No Known Activations