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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 59705
    Prev
    Next
    INDEX
    Explanations

    podcast names and topics

    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_10/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
     and
    -1.47
     inizio
    -1.24
    ↵
    -1.16
    にします
    -1.13
     still
    -1.07
    es
    -1.05
     нашего
    -1.00
    還能
    -0.99
     cuyo
    -0.99
     cyclisme
    -0.99
    POSITIVE LOGITS
    icznie
    1.35
     podcast
    1.30
    <bos>
    1.27
     étranger
    1.23
    sives
    1.22
    では
    1.18
    esthesia
    1.18
    atric
    1.16
                       
    1.15
    Advice
    1.15
    Activations Density 0.027%

    No Known Activations