© 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. 29874
    Prev
    Next
    INDEX
    Explanations

    reasoning, traffic, opened, air

    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
     indict
    0.41
     apesar
    0.41
    i
    0.40
    la
    0.40
     rolle
    0.40
     fourn
    0.40
     etc
    0.39
     caract
    0.39
    good
    0.39
    quick
    0.38
    POSITIVE LOGITS
    粝
    0.47
    ższej
    0.42
    曾在
    0.41
     질문
    0.41
     pertanyaan
    0.41
     музе
    0.41
     생각을
    0.41
    상을
    0.40
     প্রশ্নের
    0.40
    要在
    0.40
    Activations Density 0.003%

    No Known Activations