© 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. 42068
    Prev
    Next
    INDEX
    Explanations

    state abbreviations

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

    following specific words

    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
     ফস
    0.47
     NSArray
    0.46
     kafka
    0.46
     EditText
    0.45
    
    0.45
    FormData
    0.45
     HStack
    0.45
     Geschichte
    0.44
     formdata
    0.44
    вач
    0.44
    POSITIVE LOGITS
    阌
    0.47
    ताल
    0.47
    सोल
    0.46
    养
    0.45
    कृपया
    0.45
    颖
    0.45
    fea
    0.44
    უნქ
    0.44
    auk
    0.44
    kü
    0.44
    Activations Density 0.001%

    No Known Activations