© 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. 216277
    Prev
    Next
    INDEX
    Explanations

    cracked, wound, grid, rarely

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

    gleaming frying pan

    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
     hybridization
    0.50
     Workflow
    0.46
     proponent
    0.46
    ترین
    0.44
    ව
    0.43
    孅
    0.42
     foray
    0.42
     కుమార్
    0.41
     montant
    0.41
     scope
    0.40
    POSITIVE LOGITS
     กลับ
    0.49
    Ｎ
    0.49
    iten
    0.45
     皮
    0.45
    rove
    0.45
    ar
    0.44
    otras
    0.44
    itio
    0.44
    Ｍ
    0.43
     भी
    0.43
    Activations Density 0.000%

    No Known Activations