© 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. 84480
    Prev
    Next
    INDEX
    Explanations

    qualities and conditions

    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
     необходимые
    -1.25
     neste
    -1.18
    ppings
    -1.15
     mostra
    -1.13
    ingale
    -1.09
     durante
    -1.09
     เช
    -1.09
    憋
    -1.08
     tt
    -1.08
     dentro
    -1.06
    POSITIVE LOGITS
     about
    1.94
     from
    1.45
     now
    1.35
     time
    1.34
     that
    1.30
     regarding
    1.30
     since
    1.25
     several
    1.25
     INFORMACIÓN
    1.23
     Información
    1.19
    Activations Density 0.385%

    No Known Activations