© 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. 77595
    Prev
    Next
    INDEX
    Explanations

    brightness calibration

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

    prevents it

    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
    ём
    0.47
    Generated
    0.47
    Collider
    0.47
    群众
    0.46
    ␣
    0.46
    Component
    0.46
    Articulation
    0.45
    англ
    0.45
    Repeat
    0.44
    Accent
    0.44
    POSITIVE LOGITS
    rawa
    0.46
     ज्यात
    0.45
     którym
    0.44
     accessibles
    0.44
     detainees
    0.43
     faciles
    0.43
    ጄ
    0.43
     Absorption
    0.43
     absorbed
    0.42
     နှင့်
    0.42
    Activations Density 0.000%

    No Known Activations