© 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. 194890
    Prev
    Next
    INDEX
    Explanations

    Clarification or further words

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

    vivid imagery, vocational training

    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
     pourraient
    0.52
     dostęp
    0.46
     facilement
    0.45
     nėra
    0.45
     mogą
    0.45
    [...]
    0.44
     upwards
    0.44
     condiv
    0.44
     receivables
    0.43
    োজনে
    0.43
    POSITIVE LOGITS
     )
    0.49
    ０
    0.48
    踱
    0.45
     UserManager
    0.44
    陥
    0.44
     Gitar
    0.43
    淏
    0.43
    杲
    0.43
    gató
    0.43
    至
    0.42
    Activations Density 0.000%

    No Known Activations