© 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. 9136
    Prev
    Next
    INDEX
    Explanations

    Every piece

    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
     movies
    0.53
    breaks
    0.49
     Attorneys
    0.47
     needs
    0.46
     It
    0.46
    ↵
    0.46
     Movies
    0.46
     Ocho
    0.43
     Роди
    0.42
     Genres
    0.42
    POSITIVE LOGITS
    erai
    0.50
     γίνει
    0.49
    笏
    0.49
    ри
    0.48
    的过程中
    0.46
     ちゃっ
    0.46
    iniai
    0.46
    entr
    0.46
     svet
    0.45
    ***************
    0.45
    Activations Density 0.000%

    No Known Activations