© 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. 225184
    Prev
    Next
    INDEX
    Explanations

    create missing box Google learning searing

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

    your insights

    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
     situações
    0.53
     cazul
    0.52
     دیکھتے
    0.52
     situazioni
    0.49
     zainteres
    0.48
     atvej
    0.48
     Linie
    0.47
    奂
    0.47
    otiv
    0.47
     pretende
    0.47
    POSITIVE LOGITS
    𝟬
    0.50
    MER
    0.48
    0
    0.47
    BUFFER
    0.46
     byte
    0.46
    С
    0.46
     that
    0.45
    ки
    0.45
    Encoded
    0.44
    that
    0.44
    Activations Density 0.001%

    No Known Activations