© 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. 32805
    Prev
    Next
    INDEX
    Explanations

    list followed by punctuation

    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
    қ
    0.47
    кро
    0.43
    دار
    0.41
    verfahren
    0.41
     œuvre
    0.41
    ه
    0.41
    ructions
    0.40
    تان
    0.40
    дни
    0.40
    ̀
    0.40
    POSITIVE LOGITS
     stadium
    0.49
    矩阵
    0.48
    녠
    0.47
    आईपी
    0.46
     estadio
    0.46
     ascii
    0.46
    াকিং
    0.45
    ্লিষ্ট
    0.44
     matrice
    0.44
     લગભગ
    0.44
    Activations Density 0.002%

    No Known Activations