© 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. 188060
    Prev
    Next
    INDEX
    Explanations

    refills! Having done Catholic kids CSS Alumni said CDs the way keep driving

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

    risks and 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
    MS
    0.53
    api
    0.49
     recognisable
    0.48
    வால்
    0.47
    4
    0.47
     api
    0.46
    sec
    0.46
    miner
    0.45
    max
    0.45
     vents
    0.45
    POSITIVE LOGITS
     البنات
    0.49
    嬸
    0.48
    AlignedText
    0.48
    踴
    0.48
     cognitiva
    0.46
    ེ
    0.46
     اختيار
    0.45
     ನಿಜ
    0.44
    ട്ടുള്ള
    0.44
    🚶
    0.44
    Activations Density 0.001%

    No Known Activations