© 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. 107427
    Prev
    Next
    INDEX
    Explanations

    Drivers should

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

    GDPR and privacy regulations

    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
    Esta
    0.52
    licted
    0.48
    arial
    0.47
    さ
    0.46
     }_{
    0.46
    Quando
    0.45
    ಉ
    0.45
    ib
    0.45
    inari
    0.45
    atine
    0.44
    POSITIVE LOGITS
     filet
    0.54
     formContext
    0.48
     rendimiento
    0.43
     messaging
    0.43
     van
    0.42
     versión
    0.42
     mainframe
    0.42
     filets
    0.41
     mors
    0.41
     vien
    0.40
    Activations Density 0.003%

    No Known Activations