© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 57008
    Prev
    Next
    INDEX
    Explanations

    specific examples 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-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     interesados
    0.57
     exercícios
    0.55
     auxqu
    0.52
    भीर
    0.49
    作る
    0.47
     हवे
    0.47
     細胞
    0.46
     犬
    0.45
    慢性
    0.45
     इसको
    0.45
    POSITIVE LOGITS
    ة
    0.48
     larg
    0.43
    га
    0.42
     Your
    0.42
     reticulum
    0.42
    า
    0.41
     reale
    0.40
     briefcase
    0.40
    0
    0.39
    я
    0.39
    Activations Density 0.002%

    No Known Activations