© 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. 60489
    Prev
    Next
    INDEX
    Explanations

    daily informal

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

    sorry for burden

    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
    Opera
    0.60
     得
    0.50
     rezult
    0.48
    isEmpty
    0.47
    bym
    0.46
     cope
    0.46
    সিং
    0.46
    Adapter
    0.45
    thorpe
    0.45
    Parser
    0.44
    POSITIVE LOGITS
     ৩৫
    0.45
     yoj
    0.44
     क्षेत्रों
    0.43
     reparations
    0.42
     sureties
    0.41
    堰
    0.41
     रवा
    0.40
     paymentRequest
    0.40
     Афри
    0.40
    阕
    0.39
    Activations Density 0.000%

    No Known Activations