© 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. 160699
    Prev
    Next
    INDEX
    Explanations

    double to, change per, announces that

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

    avoiding common patterns

    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
    诃
    0.52
     auditors
    0.50
    軐
    0.50
     juríd
    0.49
    㡀
    0.49
     kammam
    0.48
    Gosudarstvennyj
    0.47
     accountants
    0.47
     judiciales
    0.46
     गाय
    0.46
    POSITIVE LOGITS
     reaches
    0.48
    if
    0.48
     danger
    0.47
    状
    0.47
     reaching
    0.47
    N
    0.46
    S
    0.45
    2
    0.44
    ua
    0.44
    只
    0.44
    Activations Density 0.001%

    No Known Activations