© 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. 64545
    Prev
    Next
    INDEX
    Explanations

    social well-being and times

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

    interactive components

    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
     Predicted
    0.49
    殊
    0.47
     Predictions
    0.46
    Н
    0.45
    첩
    0.45
    唿
    0.45
    У
    0.45
    Σ
    0.45
    次
    0.45
    呈
    0.44
    POSITIVE LOGITS
    ری
    0.53
     thinning
    0.48
     ежедневно
    0.47
     machines
    0.45
     retiring
    0.44
     »
    0.43
     hasn
    0.43
     ಓ
    0.43
     វា
    0.43
    ريم
    0.43
    Activations Density 0.000%

    No Known Activations