© 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. 42333
    Prev
    Next
    INDEX
    Explanations

    cover-up, fine print

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

    variations or specific subjects

    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
     unconnected
    0.47
     realistically
    0.46
     depositing
    0.46
     πραγμα
    0.46
     simplesmente
    0.44
    जग
    0.44
    發生
    0.43
    裝
    0.43
    安置
    0.42
    資
    0.42
    POSITIVE LOGITS
    er
    0.56
     Согласно
    0.49
    谄
    0.49
     Data
    0.48
    ynthia
    0.48
     Adapun
    0.47
    etern
    0.46
    എന്ന
    0.44
    al
    0.44
    ంతరం
    0.44
    Activations Density 0.000%

    No Known Activations