© 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. 93815
    Prev
    Next
    INDEX
    Explanations

    LEGO brick river

    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
    ೂರಿನ
    0.46
     connecter
    0.42
     guitarist
    0.41
    عم
    0.39
     grinders
    0.39
     fellow
    0.39
     theorist
    0.39
    #
    0.39
    噛
    0.38
    VAL
    0.38
    POSITIVE LOGITS
    诖
    0.48
    扡
    0.47
    ্ি
    0.46
     ゆっくり
    0.46
     Oliv
    0.46
    STERBEDATUM
    0.46
    䀨
    0.46
    勻
    0.45
    anyag
    0.45
    Oliv
    0.44
    Activations Density 0.001%

    No Known Activations