© 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. 158758
    Prev
    Next
    INDEX
    Explanations

    shared resources and their consequences

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

    transaction and sequence indicators

    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
     Объ
    0.49
    OSE
    0.47
    ismen
    0.47
    indre
    0.43
     몰
    0.43
    ueness
    0.42
    loat
    0.42
     (
    0.41
    lyn
    0.41
    |_{
    0.41
    POSITIVE LOGITS
     acutely
    0.56
    տ
    0.53
     listy
    0.51
     complemento
    0.50
     competição
    0.50
     arquivos
    0.50
     pomoc
    0.50
     chhoti
    0.50
     conexão
    0.49
     idioma
    0.48
    Activations Density 0.000%

    No Known Activations