© 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. 38804
    Prev
    Next
    INDEX
    Explanations

    unlike older

    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
    пу
    0.57
    тур
    0.52
    น์
    0.50
    ны
    0.49
    ю
    0.48
    (),
    0.48
    Dental
    0.47
    ،
    0.47
    грам
    0.47
    ктери
    0.46
    POSITIVE LOGITS
     infliction
    0.52
     shoving
    0.47
     nobility
    0.46
    watching
    0.46
     resemble
    0.45
     ताकत
    0.45
     sadistic
    0.45
     desper
    0.45
     insanely
    0.45
     stardom
    0.44
    Activations Density 0.008%

    No Known Activations