© 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. 204354
    Prev
    Next
    INDEX
    Explanations

    cocaine importation

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

    X is Y classification

    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
     correspondents
    0.48
    ين
    0.48
     correspon
    0.45
     NUMBER
    0.45
    INGS
    0.44
     VALUES
    0.44
    ----\
    0.43
     modelos
    0.42
    قدم
    0.42
    ANES
    0.42
    POSITIVE LOGITS
    ın
    0.48
    ่อย
    0.48
    èrement
    0.47
    ༽
    0.46
     фаразлары
    0.45
    outing
    0.45
    浈
    0.45
     दाह
    0.44
    ๋ยว
    0.44
     पक्षा
    0.43
    Activations Density 0.000%

    No Known Activations