© 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. 101213
    Prev
    Next
    INDEX
    Explanations

    language-agnostic concepts

    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
    ،
    0.45
    satz
    0.43
    的速度
    0.42
    绀
    0.42
    开了
    0.42
    MATIC
    0.41
     velocidades
    0.41
    скетбол
    0.40
    velocity
    0.39
    诊断
    0.39
    POSITIVE LOGITS
     to
    0.45
    ਰ
    0.44
    vina
    0.44
    م
    0.44
    کم
    0.43
     যাবতীয়
    0.42
     전부
    0.41
     quienes
    0.41
     quanto
    0.41
     attuale
    0.40
    Activations Density 0.004%

    No Known Activations