© 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. 116467
    Prev
    Next
    INDEX
    Explanations

    If not add, preference in, off the

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

    code, medical, and discussions

    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
     ছেলেরা
    0.49
     हीरे
    0.46
     cats
    0.44
     poisoned
    0.44
     मिल्क
    0.44
    甯
    0.44
    customers
    0.43
    找出
    0.42
     chicks
    0.42
    brother
    0.41
    POSITIVE LOGITS
    ורך
    0.46
     ensuing
    0.44
    єю
    0.44
     服务
    0.43
    เปิด
    0.42
    该
    0.41
    زد
    0.41
    седнев
    0.40
     کھیل
    0.40
    𒉰
    0.40
    Activations Density 0.000%

    No Known Activations