© 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. 130353
    Prev
    Next
    INDEX
    Explanations

    buyers need to supply

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

    balanced lifestyle

    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
     overhear
    0.49
    _{-}\
    0.48
    并购
    0.43
    Storia
    0.43
    റുക
    0.43
    лу
    0.43
    五年
    0.43
     tenter
    0.43
    StoredKeys
    0.42
    managerpage
    0.42
    POSITIVE LOGITS
     침
    0.47
    uppe
    0.46
     Millennium
    0.46
     सन्
    0.45
     consideration
    0.44
     मेड
    0.43
     balanced
    0.43
     Dunes
    0.42
     เนื่อง
    0.42
     booming
    0.41
    Activations Density 0.006%

    No Known Activations