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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 19902
    Prev
    Next
    INDEX
    Explanations

    Initial Russian

    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
     extensión
    0.51
     είναι
    0.48
    ン
    0.47
     chủng
    0.47
    ה
    0.46
     アル
    0.45
     ದೇ
    0.45
     édition
    0.44
    a
    0.44
     potete
    0.44
    POSITIVE LOGITS
    8
    0.48
    ств
    0.45
    itations
    0.44
    4
    0.44
    9
    0.44
    indazole
    0.44
    lenen
    0.43
    5
    0.43
    واء
    0.43
    తో
    0.42
    Activations Density 0.001%

    No Known Activations