© 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. 13883
    Prev
    Next
    INDEX
    Explanations

    derived from

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

    harm or negative 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
    hhhhhhhh
    0.50
    不
    0.49
    ять
    0.49
     smothered
    0.49
    loud
    0.47
     deft
    0.47
    하는데
    0.47
    ר
    0.47
    晩
    0.46
     registrados
    0.46
    POSITIVE LOGITS
     Lei
    0.48
     গ
    0.47
     Questionnaire
    0.46
     দৈর্ঘ
    0.45
     আলোকে
    0.45
     ചരി
    0.44
     মোক
    0.44
    și
    0.43
     zichzelf
    0.43
     diversi
    0.43
    Activations Density 0.000%

    No Known Activations