© 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. 190133
    Prev
    Next
    INDEX
    Explanations

    government supply chains

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

    statements and humor

    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
    ڑے
    0.47
    weisen
    0.46
    larının
    0.46
    sorption
    0.46
     fixé
    0.45
     Installation
    0.44
    <unused92>
    0.44
     Fix
    0.44
    시키는
    0.43
     admissibility
    0.43
    POSITIVE LOGITS
    ',
    0.49
     antiguos
    0.47
     soaked
    0.45
    dal
    0.43
     '
    0.43
     önemli
    0.43
    ​
    0.42
    臃
    0.42
     ⿱
    0.41
    臆
    0.41
    Activations Density 0.000%

    No Known Activations