© 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. 14097
    Prev
    Next
    INDEX
    Explanations

    systems and processes

    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
    ''''
    -1.38
     rencont
    -1.38
     Ministre
    -1.37
     ihres
    -1.34
    尴尬
    -1.33
    anguardia
    -1.31
    ——-
    -1.29
    eek
    -1.29
    wants
    -1.29
    >>>>>>>>
    -1.25
    POSITIVE LOGITS
     and
    1.70
    født
    1.30
     but
    1.27
     also
    1.24
    احة
    1.22
     always
    1.21
     refuge
    1.20
    ktör
    1.20
    erequisites
    1.20
    noční
    1.18
    Activations Density 0.275%

    No Known Activations