© 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. 231708
    Prev
    Next
    INDEX
    Explanations

    conclusion. installation. capacity. result. stage. solely. about. isotopic

    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
     চলবে
    0.54
    ScriptBuf
    0.50
    妷
    0.50
     ሽፋን
    0.47
    неоп
    0.46
     rejecting
    0.46
     νέα
    0.45
    絊
    0.45
    㳚
    0.45
    㖅
    0.44
    POSITIVE LOGITS
    ocal
    0.61
    ocy
    0.55
    oin
    0.54
    ère
    0.54
    urous
    0.50
    óz
    0.47
    OCI
    0.47
    éré
    0.46
    that
    0.45
    uur
    0.45
    Activations Density 0.001%

    No Known Activations