© 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. 110428
    Prev
    Next
    INDEX
    Explanations

    glass bulb

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

    polishing lens

    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
     硬
    0.53
    lifecycle
    0.52
     丶
    0.50
    㐰
    0.50
     Ανακτήθηκε
    0.50
    hull
    0.49
    電車
    0.48
     रोप
    0.48
    нном
    0.47
    一個人
    0.46
    POSITIVE LOGITS
     Formula
    0.56
     Fórmula
    0.51
    ⵚ
    0.50
     fórmula
    0.47
    Formula
    0.47
    ര്
    0.46
    ین
    0.45
    Ü
    0.45
    TableName
    0.44
    ц
    0.43
    Activations Density 0.002%

    No Known Activations