Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 16223
    Prev
    Next
    INDEX
    Explanations

    following common introductory phrases

    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
    蝮
    0.53
     vuttam
    0.48
    '-
    0.46
     Lavender
    0.43
    达
    0.43
    的支持
    0.42
    Aeonium
    0.42
    /
    0.42
    кте
    0.41
    }*/
    0.41
    POSITIVE LOGITS
    moins
    0.46
     fermeture
    0.46
    ствия
    0.45
    quoi
    0.44
    oinen
    0.43
     enfim
    0.43
    라는
    0.42
    imacy
    0.42
    ৈর
    0.42
    iniai
    0.41
    Activations Density 0.001%

    No Known Activations