© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 43796
    Prev
    Next
    INDEX
    Explanations

    HTML transitional doctype declarations

    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
     its
    -1.82
    ℒ
    -1.23
    <b>
    -1.22
     ($('#
    -1.22
     include
    -1.20
     our
    -1.17
     a
    -1.16
    &,
    -1.16
     my
    -1.15
    仍然
    -1.14
    POSITIVE LOGITS
     to
    1.63
     varandra
    1.38
     専用
    1.35
     biß
    1.32
    獁
    1.31
     onPostExecute
    1.29
     relato
    1.27
    </em>
    1.27
    Биография
    1.26
    谘
    1.25
    Activations Density 0.023%

    No Known Activations