© 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. 233275
    Prev
    Next
    INDEX
    Explanations

    illegal or found contraband

    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
     başlay
    0.46
    一开始
    0.46
    大规模
    0.44
     iniziare
    0.41
    🙋
    0.41
     pierws
    0.41
     શહેર
    0.40
    可持续
    0.40
    桕
    0.40
     bắt
    0.40
    POSITIVE LOGITS
     illegally
    0.58
     evidence
    0.54
     illegal
    0.52
     bags
    0.51
     ilegal
    0.49
     अवैध
    0.49
    非法
    0.48
     stolen
    0.48
     Evidence
    0.47
     pouches
    0.47
    Activations Density 0.037%

    No Known Activations