© 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. 125319
    Prev
    Next
    INDEX
    Explanations

    security claims, removal, mutations

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

    joint monarchs, Spain

    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
    рует
    0.42
    匕
    0.41
    ست
    0.41
    prepare
    0.40
    profile
    0.40
    ב
    0.40
    }\|_{
    0.40
     اين
    0.39
    리학
    0.39
    あくまで
    0.39
    POSITIVE LOGITS
     інших
    0.57
     Directive
    0.50
     levies
    0.47
    dzie
    0.46
     prescriptions
    0.46
     освіти
    0.46
     Schemes
    0.46
     سیاسی
    0.44
     contralateral
    0.44
    ’
    0.44
    Activations Density 0.001%

    No Known Activations