© 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. 154153
    Prev
    Next
    INDEX
    Explanations

    looking forward to hearing from you

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

    livestock vanishing or disappearing

    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
    gruppe
    0.52
    nested
    0.50
    у
    0.50
    parallel
    0.48
    outer
    0.47
    ской
    0.47
    SPD
    0.47
    subunit
    0.47
    EX
    0.47
    カウント
    0.47
    POSITIVE LOGITS
     Pines
    0.49
     *****
    0.45
     tár
    0.44
     Chichester
    0.43
    剐
    0.43
     发表
    0.42
    处理器
    0.42
    罗马
    0.41
    披露
    0.41
     Avon
    0.41
    Activations Density 0.000%

    No Known Activations