© 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. 112384
    Prev
    Next
    INDEX
    Explanations

    or alternatively

    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
    sequently
    -1.43
     but
    -1.35
     PUSTAKA
    -1.32
     any
    -1.26
     one
    -1.23
     maar
    -1.22
    ارتمان
    -1.20
    any
    -1.20
     কো
    -1.19
    anyone
    -1.18
    POSITIVE LOGITS
    ，“
    1.47
    ’
    1.41
     ‘
    1.35
    ‘
    1.34
    ’;
    1.34
    u
    1.31
    ”:
    1.23
    ’:
    1.23
     Preferred
    1.23
    ,’
    1.21
    Activations Density 0.004%

    No Known Activations