© 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. 182872
    Prev
    Next
    INDEX
    Explanations

    declaration of friendship

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

    examples and instructions

    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
     trunk
    0.52
    蓁
    0.47
     truncation
    0.46
    雖然
    0.45
     fumar
    0.45
    摽
    0.45
     المملكة
    0.44
     trunc
    0.44
     Marn
    0.44
    醌
    0.44
    POSITIVE LOGITS
    gä
    0.49
    序
    0.48
    ä
    0.47
    ön
    0.46
    YG
    0.46
    VARIABLE
    0.45
     bénéficier
    0.45
    ং
    0.44
    essori
    0.44
    コーヒー
    0.44
    Activations Density 0.000%

    No Known Activations