© 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. 143856
    Prev
    Next
    INDEX
    Explanations

    list definitions

    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
     caus
    0.54
     drought
    0.42
     chemically
    0.41
    ])));
    0.41
    分からない
    0.41
    Lightbox
    0.41
     crime
    0.40
     gelişmeler
    0.39
     refuse
    0.39
    లిన
    0.39
    POSITIVE LOGITS
    الع
    0.45
    整个
    0.44
     Distributions
    0.43
    ulitan
    0.43
    ச
    0.43
    ontiti
    0.43
    sensitivity
    0.43
     itali
    0.43
    alin
    0.42
     বৎসরের
    0.42
    Activations Density 0.000%

    No Known Activations