© 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. 692
    Prev
    Next
    INDEX
    Explanations

    Multiple choice questions

    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
    kách
    0.37
    ాన్ని
    0.36
    kého
    0.36
    жнему
    0.33
    ੇ
    0.33
    iség
    0.32
    ných
    0.32
     dement
    0.32
    ጣም
    0.31
    Transaksi
    0.31
    POSITIVE LOGITS
    н
    0.55
     on
    0.51
    s
    0.46
    и
    0.44
    ╯
    0.43
    ב
    0.42
     I
    0.42
    この
    0.42
    if
    0.39
    ों
    0.39
    Activations Density 0.138%

    No Known Activations