© 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. 193632
    Prev
    Next
    INDEX
    Explanations

    benefit-risk assessment

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

    install them, approve payments, start typing

    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
     샤
    0.49
    ol
    0.47
    ado
    0.46
     কাছে
    0.45
    ছাড়া
    0.43
     מב
    0.42
    andy
    0.41
     cafe
    0.41
     간
    0.41
     효율
    0.40
    POSITIVE LOGITS
     Itália
    0.54
     âge
    0.52
     appartenant
    0.52
     appartiennent
    0.52
     utilisent
    0.49
     Règ
    0.47
     linguagem
    0.47
     planis
    0.47
    ウォッチ
    0.47
     História
    0.46
    Activations Density 0.001%

    No Known Activations