© 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. 235157
    Prev
    Next
    INDEX
    Explanations

    action based on 'to'

    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
     piş
    0.62
    ҝ
    0.59
    ctive
    0.58
     anlaş
    0.58
    ct
    0.57
     mlij
    0.57
    parametrize
    0.57
    不支持
    0.56
     grasa
    0.55
    𝕟
    0.55
    POSITIVE LOGITS
    0.50
    Wake
    0.49
    Ella
    0.49
    Youth
    0.49
    Sam
    0.48
    Pom
    0.48
     Wake
    0.48
     RDA
    0.47
     Youth
    0.47
    EP
    0.46
    Activations Density 0.000%

    No Known Activations