© 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. 104305
    Prev
    Next
    INDEX
    Explanations

    neighborhood dogs

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

    computer engineer valuable materials

    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
    charge
    0.48
    тами
    0.44
    는
    0.42
    uff
    0.41
    }=(\
    0.41
    aren
    0.41
     orphans
    0.40
    ventions
    0.39
    Charge
    0.39
    载
    0.39
    POSITIVE LOGITS
    »),
    0.57
     limitée
    0.54
    浠
    0.52
     rozpoczę
    0.48
     WITH
    0.48
     neke
    0.48
     Schritte
    0.47
     உள்ளிட்ட
    0.47
     BlackBerry
    0.47
     स्टेज
    0.47
    Activations Density 0.000%

    No Known Activations