© 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. 48402
    Prev
    Next
    INDEX
    Explanations

    estimated duration or length

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

    promotes harm and violence

    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
     shadowy
    0.46
     กัน
    0.42
     Ян
    0.41
     questionnaires
    0.41
     ഗ്ര
    0.40
     꾸
    0.40
     साल
    0.39
     thinning
    0.39
     glimpses
    0.39
    我觉得
    0.39
    POSITIVE LOGITS
    CDATA
    0.45
    butanol
    0.44
    :&
    0.43
    Chu
    0.42
    تقدم
    0.42
    шина
    0.42
    Duel
    0.42
    φέρον
    0.42
    DrvGPIO
    0.41
    স্থলে
    0.41
    Activations Density 0.000%

    No Known Activations