© 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. 16-GEMMASCOPE-2-RES-262K
    7. 120251
    Prev
    Next
    INDEX
    Explanations

    noodle soup

    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
    ified
    0.52
    ugu
    0.52
    d
    0.50
    O
    0.50
    quisite
    0.48
     punctuation
    0.48
    opher
    0.47
     levant
    0.47
    pped
    0.46
    ‣
    0.46
    POSITIVE LOGITS
    闿
    0.60
    א
    0.58
    ان
    0.57
    צ
    0.54
    रातील
    0.53
     Corrosion
    0.53
    闓
    0.53
    אן
    0.52
     araştırm
    0.51
    茈
    0.50
    Activations Density 0.000%

    No Known Activations