© 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. 49020
    Prev
    Next
    INDEX
    Explanations

    foreign words and characters

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

    looking for initial actions or checks

    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
     operational
    0.42
     rag
    0.41
     operation
    0.40
     price
    0.40
     bias
    0.40
     operations
    0.39
     refract
    0.39
    操
    0.39
     review
    0.38
     feather
    0.38
    POSITIVE LOGITS
    aliśmy
    0.46
    笑着
    0.46
     compartilh
    0.46
     एक्सप्ले
    0.46
    确
    0.45
     puriso
    0.45
    ച്ചി
    0.44
     compartió
    0.44
    ګ
    0.44
     সত্যিই
    0.44
    Activations Density 0.000%

    No Known Activations