© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 34721
    Prev
    Next
    INDEX
    Explanations

    influences the tone

    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
    는
    0.54
     др
    0.48
    йте
    0.46
    ;
    0.46
    是
    0.46
     அவை
    0.43
     tân
    0.43
    :
    0.43
     awaited
    0.43
     अन्य
    0.42
    POSITIVE LOGITS
     způ
    0.45
     காமெடி
    0.42
     laiss
    0.42
     تړ
    0.41
     daqui
    0.41
    opro
    0.40
     ministro
    0.40
     Hrvatskoj
    0.40
    andfeel
    0.40
     profesores
    0.40
    Activations Density 0.001%

    No Known Activations