© 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. 195067
    Prev
    Next
    INDEX
    Explanations

    common phrases and contexts

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

    weapons of destruction

    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
     FIX
    0.42
     特許庁
    0.42
     oltre
    0.41
     편리
    0.40
    FRINGEMENT
    0.40
     Siamo
    0.40
    :'],
    0.40
     고급
    0.40
    市场
    0.39
     mily
    0.39
    POSITIVE LOGITS
    oes
    0.52
    తుందని
    0.50
    ány
    0.48
    set
    0.47
     waarvan
    0.47
    aiman
    0.47
    assa
    0.46
    making
    0.46
    etur
    0.46
    aña
    0.46
    Activations Density 0.000%

    No Known Activations