© 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. 111122
    Prev
    Next
    INDEX
    Explanations

    continue or quit prompt

    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
     cinemas
    0.43
     Self
    0.42
     newline
    0.42
     narrative
    0.41
     cozy
    0.41
     gob
    0.40
     harnessing
    0.40
    謐
    0.40
     Millennials
    0.40
     archive
    0.39
    POSITIVE LOGITS
    ateur
    0.51
    resultado
    0.51
     gespre
    0.49
    ents
    0.47
    Removing
    0.47
    stArray
    0.47
    вед
    0.47
    Hou
    0.47
    emand
    0.46
    assadors
    0.46
    Activations Density 0.000%

    No Known Activations