© 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. 227128
    Prev
    Next
    INDEX
    Explanations

    screen classifier

    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
     المراجعه
    0.59
     اللغه
    0.58
    哆
    0.55
     Unterstüt
    0.54
     Handlung
    0.48
    ostí
    0.48
    蚌
    0.48
    ப்படுத்த
    0.47
    yección
    0.47
     konz
    0.47
    POSITIVE LOGITS
    PUBLIC
    0.45
     obliged
    0.43
     reared
    0.41
    니
    0.40
     await
    0.40
    BOUND
    0.39
     demanded
    0.39
     rearing
    0.39
     bakar
    0.39
     जन्
    0.39
    Activations Density 0.001%

    No Known Activations