© 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. 50505
    Prev
    Next
    INDEX
    Explanations

    schedule

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

    legal or forbidden actions

    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
     सुर्खियों
    0.53
    ٨
    0.48
     freaking
    0.47
    ayama
    0.47
     clenched
    0.46
    ۸
    0.45
    black
    0.45
    tdown
    0.45
    currencies
    0.45
    conferences
    0.44
    POSITIVE LOGITS
     SCALE
    0.52
    0.48
    法
    0.48
     economy
    0.47
    钩
    0.47
     incorporation
    0.46
     resources
    0.45
    らい
    0.45
     CAPACITY
    0.45
     قي
    0.44
    Activations Density 0.000%

    No Known Activations