© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 3209
    Prev
    Next
    INDEX
    Explanations

    ability to perform actions

    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
     wären
    0.23
     seront
    0.22
     shoes
    0.21
    㑬
    0.20
    physiology
    0.20
    ১৩
    0.20
    ции
    0.20
    вается
    0.20
    ],
    0.20
     není
    0.20
    POSITIVE LOGITS
     να
    0.53
     to
    0.41
    ที่จะ
    0.35
     upang
    0.35
     să
    0.34
    to
    0.32
    ToRemove
    0.32
     để
    0.31
    ToSend
    0.30
    ToDelete
    0.29
    Activations Density 0.538%

    No Known Activations