© 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-16K
    7. 13575
    Prev
    Next
    INDEX
    Explanations

    documentation, IVD, risk management

    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_16k_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
    oruč
    0.47
    -
    0.47
     Steps
    0.45
     memiliki
    0.45
    ắm
    0.45
    ќ
    0.44
    fordshire
    0.44
     zespół
    0.44
     Gel
    0.44
     Еще
    0.44
    POSITIVE LOGITS
    クトル
    0.55
    。<
    0.51
    土壤
    0.50
    ரஜன்
    0.50
     그
    0.49
    %。
    0.49
    以後
    0.48
    。"
    0.48
     prejudices
    0.48
    ILIA
    0.47
    Activations Density 0.021%

    No Known Activations