© 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. 139595
    Prev
    Next
    INDEX
    Explanations

    website linkage and technical terms

    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
    其
    0.50
    uições
    0.47
    ственных
    0.44
    E
    0.42
    γρα
    0.41
    اما
    0.40
    ↵
    0.39
    composed
    0.39
     Van
    0.38
    مح
    0.38
    POSITIVE LOGITS
     Goog
    0.54
    脓
    0.52
     brutal
    0.51
     administr
    0.50
     дзяржа
    0.50
     deplorable
    0.50
    INGO
    0.49
     говорили
    0.49
     rotund
    0.48
     gorg
    0.48
    Activations Density 0.004%

    No Known Activations