© 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. 141874
    Prev
    Next
    INDEX
    Explanations

    information reliable

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

    explaining choices and options

    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
    欸
    0.48
    φε
    0.45
    עות
    0.43
    കട
    0.41
    ետ
    0.41
     حم
    0.41
    مي
    0.41
     лікар
    0.40
     dreamer
    0.40
    病人
    0.40
    POSITIVE LOGITS
    p
    0.61
    Wir
    0.60
    w
    0.57
    n
    0.55
    U
    0.54
    t
    0.54
    Mont
    0.53
    c
    0.53
    I
    0.52
    l
    0.50
    Activations Density 0.000%

    No Known Activations