© 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. 117204
    Prev
    Next
    INDEX
    Explanations

    get ready

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

    inhibition and inhibitor

    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
    çok
    0.55
     année
    0.50
    ␊
    0.49
     त्या
    0.47
     vuelta
    0.47
     Catedral
    0.47
     reduziert
    0.46
     velho
    0.46
     กี้
    0.46
     стару
    0.46
    POSITIVE LOGITS
     Write
    0.50
     March
    0.50
     Do
    0.47
     P
    0.47
     Co
    0.43
     Illustration
    0.43
     How
    0.42
     Video
    0.42
     Read
    0.42
    Write
    0.41
    Activations Density 0.000%

    No Known Activations