© 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. 61287
    Prev
    Next
    INDEX
    Explanations

    competitions

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

    academic or technical terms

    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
    価格
    0.46
     価格
    0.46
    適合
    0.45
     RESP
    0.43
     Nghị
    0.43
    📢
    0.43
     선택
    0.42
     сила
    0.42
    🖉
    0.42
     साहस
    0.42
    POSITIVE LOGITS
    0.50
    if
    0.48
    BL
    0.46
    Wet
    0.46
    ilem
    0.46
    ili
    0.45
    ftl
    0.45
    icks
    0.44
    FW
    0.44
    ift
    0.44
    Activations Density 0.000%

    No Known Activations