© 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. 235158
    Prev
    Next
    INDEX
    Explanations

    locations, events, winners, and global occurrences

    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
     опас
    0.54
    і
    0.47
    х
    0.47
    т
    0.46
    че
    0.45
    something
    0.44
    टी
    0.44
    _
    0.44
    йн
    0.43
    тва
    0.43
    POSITIVE LOGITS
     reconnaît
    0.55
     predicts
    0.50
     anticipates
    0.48
     কর্মসূ
    0.47
    とに
    0.46
     modelling
    0.45
     ressources
    0.44
     PKD
    0.44
     bioquímica
    0.44
    客户端
    0.44
    Activations Density 0.000%

    No Known Activations