© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 13101
    Prev
    Next
    INDEX
    Explanations

    file or code headers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ྄
    -1.33
    ikusbot
    -1.24
    ⤦
    -1.23
    indows
    -1.23
     geringe
    -1.20
    ЛУ
    -1.19
    ughter
    -1.17
    ampe
    -1.16
    icolor
    -1.16
     dizendo
    -1.16
    POSITIVE LOGITS
     with
    1.20
     specified
    1.16
     possibly
    1.06
     stated
    1.05
    le
    1.02
     information
    1.01
     until
    1.00
     bolster
    0.99
    k
    0.98
    地に
    0.97
    Activations Density 0.003%

    No Known Activations