© 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. 68705
    Prev
    Next
    INDEX
    Explanations

    first accurate count

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

    financial actions merging

    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
    痳
    0.56
    ंची
    0.50
    昨天
    0.48
    前辈
    0.48
    omba
    0.48
    强
    0.47
     viendo
    0.47
    东
    0.47
     שת
    0.46
    钻石
    0.46
    POSITIVE LOGITS
    کس
    0.55
    frozen
    0.48
    WEIGHT
    0.47
     overweight
    0.47
     convolutions
    0.46
    ва
    0.46
     merged
    0.46
    quartered
    0.46
     گوش
    0.46
    weight
    0.45
    Activations Density 0.000%

    No Known Activations