© 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. 41320
    Prev
    Next
    INDEX
    Explanations

    rewards and offers

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

    corrections and explanations

    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
    സും
    0.49
    ങ്ങളും
    0.47
    ンダント
    0.46
    !”.
    0.46
    ंद्व
    0.45
    <unused564>
    0.45
    ství
    0.45
    <unused430>
    0.44
     каждому
    0.43
    perturbed
    0.43
    POSITIVE LOGITS
     cogn
    0.45
    モ
    0.44
    ़
    0.44
    可惜
    0.42
     negro
    0.42
    Pri
    0.41
    idene
    0.41
     obras
    0.40
     dichas
    0.40
     builder
    0.40
    Activations Density 0.000%

    No Known Activations