© 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. 35722
    Prev
    Next
    INDEX
    Explanations

    http:// or bit.ly

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

    Salesforce CRM

    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
    that
    0.55
    、
    0.50
    觓
    0.50
     یا
    0.49
     অস
    0.48
     that
    0.47
    って
    0.47
     Or
    0.46
    装
    0.45
    at
    0.45
    POSITIVE LOGITS
    UTER
    0.64
    ści
    0.59
     osobe
    0.51
    ING
    0.50
     ROUILLER
    0.49
     deced
    0.49
     proverbial
    0.49
    ET
    0.49
    OTE
    0.48
    RENDITION
    0.48
    Activations Density 0.003%

    No Known Activations