© 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. 4001
    Prev
    Next
    INDEX
    Explanations

    such as

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

    steal your money

    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
    у
    0.65
    {
    0.58
    EX
    0.52
    тя
    0.49
    {~
    0.49
    Prosec
    0.49
    1
    0.49
    on
    0.47
    cook
    0.47
    j
    0.47
    POSITIVE LOGITS
     Gaines
    0.56
     ఉత్త
    0.55
     σήμερα
    0.53
     Hoover
    0.53
     మంచి
    0.52
     tomates
    0.52
     deltaTime
    0.52
     gode
    0.51
     然后
    0.50
     πυ
    0.49
    Activations Density 0.000%

    No Known Activations