© 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. 21371
    Prev
    Next
    INDEX
    Explanations

    code block terminators like `';'` `,`

    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
    दुर्ग
    0.41
    Charm
    0.39
    мино
    0.39
    ప్రత్య
    0.39
    malıdır
    0.38
    rile
    0.38
    rocess
    0.38
    ò
    0.37
    ▍
    0.37
    phed
    0.37
    POSITIVE LOGITS
     car
    0.46
     RNG
    0.46
     roul
    0.45
     Camb
    0.45
     favorite
    0.44
     Cambodian
    0.44
     projet
    0.43
     Chrysler
    0.43
     frisch
    0.43
     Kamal
    0.42
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.