© 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. 213180
    Prev
    Next
    INDEX
    Explanations

    charged and ready

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

    what they need

    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
    문에
    0.49
     envol
    0.49
    ພວກເຮ
    0.47
    Payment
    0.46
    ()-
    0.45
    routingHeader
    0.45
     associa
    0.43
    trashItem
    0.43
    ဝန်
    0.43
    AllResult
    0.43
    POSITIVE LOGITS
     digo
    0.44
    dua
    0.43
    rie
    0.43
     pengunjung
    0.43
     reduzir
    0.42
    quelle
    0.42
    iso
    0.42
     pengurangan
    0.41
    1
    0.41
    igh
    0.41
    Activations Density 0.000%

    No Known Activations