© 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. 114106
    Prev
    Next
    INDEX
    Explanations

    entities and connectives

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

    commands or examples

    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
    Negative Logits
    kon
    0.51
     gefunden
    0.47
    tab
    0.47
    venuto
    0.46
     kennt
    0.46
    ffen
    0.46
    tn
    0.45
    kező
    0.44
    ()}')
    0.44
     respekt
    0.43
    POSITIVE LOGITS
     coarse
    0.50
    όμε
    0.46
    ू
    0.45
     JCB
    0.45
    ุ่ม
    0.45
     SOFTWARE
    0.44
    りが
    0.44
    цам
    0.44
     LOSS
    0.43
    领取
    0.43
    Activations Density 0.001%

    No Known Activations