© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 112766
    Prev
    Next
    INDEX
    Explanations

    sufficient enough

    np_acts-logits-general · gemini-2.5-flash-lite

    planning and developing strategies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     quibusdam
    0.48
    Branches
    0.48
    Chance
    0.46
    甚
    0.43
    EZ
    0.41
     Erweiter
    0.41
    Damage
    0.40
    ダメージ
    0.40
    Dihydro
    0.40
    Celebr
    0.40
    POSITIVE LOGITS
    分别
    0.48
     미리
    0.48
     proactively
    0.46
     각
    0.45
    üml
    0.44
    सूची
    0.44
     чита
    0.43
    addena
    0.43
     충분
    0.43
     å
    0.43
    Activations Density 0.000%

    No Known Activations