© 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. 40-GEMMASCOPE-2-RES-262K
    7. 6081
    Prev
    Next
    INDEX
    Explanations

    for followed by purpose or pronoun

    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_40_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
    in
    0.25
    y
    0.21
    ipation
    0.20
    ependence
    0.20
    o
    0.20
    ا
    0.20
    >";
    0.20
    ת
    0.20
    ilization
    0.20
     Possible
    0.19
    POSITIVE LOGITS
    geries
    0.36
    erun
    0.36
     awhile
    0.35
     starters
    0.33
     purposes
    0.29
     reals
    0.28
     each
    0.28
    ked
    0.27
     sake
    0.27
    erunner
    0.26
    Activations Density 0.103%

    No Known Activations