© 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. 83659
    Prev
    Next
    INDEX
    Explanations

    artists, education, people, all

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

    unauthorised access

    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
    ،
    0.60
    “.
    0.55
    毽
    0.52
    ၊
    0.49
    녜
    0.49
    ”:
    0.48
    يلا
    0.48
    ଈ
    0.48
    ፣
    0.48
    မြင့်
    0.47
    POSITIVE LOGITS
    quela
    0.48
     ہوسکتا
    0.46
    aler
    0.46
     siebie
    0.46
    <unused692>
    0.46
    <unused398>
    0.44
    ri
    0.43
     orchestrated
    0.43
     promoted
    0.43
     invaded
    0.43
    Activations Density 0.000%

    No Known Activations