© 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. 175931
    Prev
    Next
    INDEX
    Explanations

    after the fact welcome now willing journalist groups ingredients

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

    customization, datasets, seamless, permanent, infected

    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
     इंत
    0.48
    RAR
    0.46
    ٹوں
    0.46
    Prov
    0.45
    细胞
    0.45
    鼈
    0.44
    MAP
    0.44
    ROOM
    0.43
    надцати
    0.43
    trad
    0.43
    POSITIVE LOGITS
    alla
    0.49
    ă
    0.44
    byId
    0.44
    udi
    0.43
    在中
    0.43
     ሃ
    0.43
     spook
    0.43
    uda
    0.43
     Sản
    0.42
    ((
    0.42
    Activations Density 0.001%

    No Known Activations