© 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. 235952
    Prev
    Next
    INDEX
    Explanations

    describing states, actions, or construction

    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
    గ్
    0.47
    سپ
    0.46
    ，
    0.46
    肯
    0.45
     settled
    0.41
    })/
    0.41
    জুর
    0.41
    ம்த
    0.41
    كه
    0.40
    гән
    0.39
    POSITIVE LOGITS
     понрави
    0.52
     ошибок
    0.48
     놓
    0.46
     장애
    0.46
     пау
    0.46
     प्रैक्ट
    0.45
    asana
    0.45
    ⟋
    0.44
     РО
    0.44
    ̎
    0.44
    Activations Density 0.003%

    No Known Activations