© 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. 74138
    Prev
    Next
    INDEX
    Explanations

    quantization and capitalization

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

    creating resources or live data

    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
     Spar
    0.44
    spedes
    0.44
     Paribas
    0.44
    mse
    0.43
     Ran
    0.43
    运算
    0.43
     |
    0.42
     births
    0.41
     चित
    0.40
     Clone
    0.39
    POSITIVE LOGITS
     thanking
    0.47
    শংস
    0.44
    तोंडा
    0.44
     സെക്ര
    0.43
     エン
    0.42
     creativo
    0.42
     abrazo
    0.42
    👄
    0.42
    Appro
    0.42
    и
    0.42
    Activations Density 0.000%

    No Known Activations