© 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. 117282
    Prev
    Next
    INDEX
    Explanations

    blues jams, true responsibility, expected to

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

    technical or research descriptions

    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
     पोट
    0.60
     détermination
    0.53
     lull
    0.52
    ᅪ
    0.49
     انجام
    0.49
     युद्ध
    0.49
     전쟁
    0.49
     甲
    0.48
    들과
    0.47
    VARIABLE
    0.47
    POSITIVE LOGITS
    櫚
    0.51
    ів
    0.50
    م
    0.50
     edited
    0.48
     reels
    0.46
    يت
    0.46
    ن
    0.45
    iese
    0.45
     alienated
    0.45
    ის
    0.45
    Activations Density 0.000%

    No Known Activations