© 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. 16-GEMMASCOPE-2-RES-262K
    4. 9576
    Prev
    Next
    INDEX
    Explanations

    do not

    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_16_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
    責
    0.47
    簡
    0.46
     neon
    0.46
     Donec
    0.46
    ައި
    0.46
     poświę
    0.46
    ဆိုင်
    0.45
    דע
    0.45
    ﭜ
    0.44
    𝚓
    0.44
    POSITIVE LOGITS
     अम्ब
    0.48
    </u>
    0.47
    uk
    0.47
    থ্যা
    0.45
    yl
    0.45
     telas
    0.44
    epsilon
    0.44
    ographically
    0.44
    unjukan
    0.43
    id
    0.42
    Activations Density 0.000%

    No Known Activations