© 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. 108429
    Prev
    Next
    INDEX
    Explanations

    common in language

    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
     having
    0.46
     residing
    0.45
    Having
    0.44
     Aloha
    0.40
    ้
    0.39
    Hiện
    0.39
     posiad
    0.39
    s
    0.39
    मध्य
    0.38
    IFICATION
    0.38
    POSITIVE LOGITS
     rubbish
    0.48
    𐰴
    0.44
    jö
    0.44
     supermarkets
    0.43
     políticos
    0.42
    uncu
    0.42
     результа
    0.42
    했지만
    0.42
    లిన
    0.42
    overnment
    0.42
    Activations Density 0.004%

    No Known Activations