© 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-65K
    7. 2759
    Prev
    Next
    INDEX
    Explanations

    about yourself

    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_65k_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
     для
    0.44
     preferentially
    0.42
    flex
    0.40
    ergic
    0.40
     $|
    0.38
    msubsup
    0.38
    induced
    0.38
     upregulated
    0.38
    <unused2155>
    0.38
    atoti
    0.38
    POSITIVE LOGITS
    自己的
    0.68
     things
    0.60
     svoje
    0.59
     своей
    0.57
     своим
    0.54
     своего
    0.54
     politics
    0.54
     نفسه
    0.53
     अपने
    0.52
    自分の
    0.51
    Activations Density 0.124%

    No Known Activations