© 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. 43445
    Prev
    Next
    INDEX
    Explanations

    building, impacts, Tacitus, Scaliger, used

    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
     discurso
    0.39
    🥳
    0.38
    Emojis
    0.37
     திரைப்படம்
    0.37
    🎄
    0.37
    境
    0.36
    ﹊
    0.36
    支部
    0.36
    訪問
    0.36
    宴
    0.36
    POSITIVE LOGITS
    ottesville
    0.45
    leveland
    0.44
     मानक
    0.43
     기타
    0.43
     உலகின்
    0.43
     feared
    0.42
    itzerland
    0.42
     சரியான
    0.42
     കഴ
    0.41
    Ϭ
    0.41
    Activations Density 0.002%

    No Known Activations