© 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. 190358
    Prev
    Next
    INDEX
    Explanations

    information or outcome

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

    different platforms and tests

    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
     س
    0.52
    胶
    0.47
    Environmental
    0.46
    Breakpoint
    0.46
     settimana
    0.45
    FIELD
    0.44
     फिल्म
    0.43
    盤
    0.43
     खोले
    0.43
    ITE
    0.43
    POSITIVE LOGITS
     espont
    0.46
    willing
    0.46
    şik
    0.46
     sociable
    0.44
     amist
    0.44
     Chom
    0.44
     altro
    0.43
    putable
    0.43
    чным
    0.43
    trusive
    0.43
    Activations Density 0.000%

    No Known Activations