© 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. 3689
    Prev
    Next
    INDEX
    Explanations

    abstract qualities and their use

    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
    ui
    0.32
    R
    0.30
    ob
    0.29
    ru
    0.29
    t
    0.29
    num
    0.29
    re
    0.28
    ork
    0.28
     Chocolate
    0.28
    ke
    0.27
    POSITIVE LOGITS
     respectivas
    0.29
     predicament
    0.29
    และ
    0.28
     envers
    0.28
    ванні
    0.27
     omnichannel
    0.27
    myLabels
    0.27
     privind
    0.27
     ও
    0.26
    성과
    0.26
    Activations Density 0.407%

    No Known Activations