© 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. 89548
    Prev
    Next
    INDEX
    Explanations

    result set

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

    calendar, probability, consequences

    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
     pretence
    0.49
     reductive
    0.49
    (,
    0.46
     წ
    0.45
     mainframe
    0.45
     quotient
    0.45
     engend
    0.45
     کوئی
    0.45
     TRANS
    0.45
     checksum
    0.44
    POSITIVE LOGITS
    Hitting
    0.46
    Mason
    0.44
    нила
    0.43
    лит
    0.43
    Vì
    0.43
    Diag
    0.43
    진
    0.42
    ецца
    0.41
    িদ্ধ
    0.41
    typen
    0.40
    Activations Density 0.000%

    No Known Activations