© 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. 4256
    Prev
    Next
    INDEX
    Explanations

    descriptions and formulations

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

    specific descriptions after labels

    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
    Lorsque
    0.48
    Jumlah
    0.47
    恐怖
    0.46
    嗥
    0.46
    ObjectTemp
    0.45
    <div>
    0.45
    पिछले
    0.44
    ร
    0.44
    सबसे
    0.44
    雎
    0.44
    POSITIVE LOGITS
     characterizes
    0.49
     pertaining
    0.49
     applicability
    0.47
     diterapkan
    0.46
     characterized
    0.46
     refers
    0.46
     chalc
    0.45
     formulations
    0.45
     formulation
    0.44
     coef
    0.44
    Activations Density 0.000%

    No Known Activations