© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 108201
    Prev
    Next
    INDEX
    Explanations

    diversity and inclusion

    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
     monocytes
    0.49
     maximising
    0.49
    較
    0.48
     uitvoering
    0.48
    три
    0.46
    Rational
    0.46
     complementarity
    0.46
     lymphocyte
    0.45
     lymphocytes
    0.44
    териа
    0.44
    POSITIVE LOGITS
     I
    0.59
     Agricultural
    0.48
     names
    0.47
     NASCAR
    0.46
     Sep
    0.44
     September
    0.44
     etx
    0.44
     Names
    0.44
    ),"
    0.43
     Let
    0.43
    Activations Density 0.004%

    No Known Activations