© 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. 120528
    Prev
    Next
    INDEX
    Explanations

    another Janet

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

    del Toro, submitted, politics, week

    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
    l
    0.56
    v
    0.47
    h
    0.46
    reise
    0.46
    i
    0.45
    erst
    0.44
    hrte
    0.42
    te
    0.42
    eres
    0.42
    a
    0.42
    POSITIVE LOGITS
     LEM
    0.53
    শক্ত
    0.52
    퍼
    0.52
     julho
    0.51
    트
    0.51
    講座
    0.48
    ޟ
    0.48
    蛎
    0.48
     trấn
    0.47
    龺
    0.47
    Activations Density 0.000%

    No Known Activations