© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 44157
    Prev
    Next
    INDEX
    Explanations

    various languages

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

    but, surprisingly

    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
     
    0.50
     niektórych
    0.47
     임
    0.43
    individual
    0.41
     лого
    0.41
    醫院
    0.40
     kuris
    0.40
     포
    0.39
     kaca
    0.39
    fk
    0.39
    POSITIVE LOGITS
     instabilities
    0.42
     درمیان
    0.42
     superposition
    0.41
     thermique
    0.41
    ంతరం
    0.41
     కథ
    0.40
    ان
    0.40
    ानंद
    0.40
    ominus
    0.39
    StaticHandler
    0.38
    Activations Density 0.000%

    No Known Activations