© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 9764
    Prev
    Next
    INDEX
    Explanations

    latex package commands

    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
    ről
    0.45
    setosa
    0.42
    ০০
    0.42
    output
    0.41
    ುತ್ತಿದೆ
    0.41
    чиго
    0.41
    ヾ
    0.41
    tobago
    0.40
    carbon
    0.40
     далі
    0.40
    POSITIVE LOGITS
     of
    0.54
     W
    0.50
    大师
    0.47
     několik
    0.43
     Cots
    0.42
     Š
    0.40
     metamorph
    0.39
    ของการ
    0.39
     Nazi
    0.39
     Ա
    0.39
    Activations Density 0.000%

    No Known Activations