© 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. 148618
    Prev
    Next
    INDEX
    Explanations

    average statistics and comparisons

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

    this is example

    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
    كلم
    0.50
    وكان
    0.46
     Ruta
    0.45
    ورك
    0.43
    ডেম
    0.41
    -
    0.41
    િયા
    0.40
    itag
    0.40
    那位
    0.40
    цията
    0.40
    POSITIVE LOGITS
    allOf
    0.51
    OM
    0.48
    error
    0.47
    bool
    0.47
    all
    0.43
     }}$.
    0.43
    bluetooth
    0.43
    BOOL
    0.43
    XXX
    0.43
    䍧
    0.43
    Activations Density 0.001%

    No Known Activations