© 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. 34-GEMMASCOPE-RES-131K
    7. 31238
    Prev
    Next
    INDEX
    Explanations

    include, Declaration, Distributed, Unknown, Test, SPDX

    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_34/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
     سپس
    -1.32
     comté
    -1.23
    あっという
    -1.21
     incrí
    -1.21
     VOUS
    -1.20
    蔸
    -1.20
     constater
    -1.20
     málaga
    -1.17
     zeven
    -1.16
     discuter
    -1.16
    POSITIVE LOGITS
    }\
    1.24
         
    1.17
    ........
    1.16
     Config
    1.13
     In
    1.12
     A
    1.10
     with
    1.09
    </i>
    1.09
     h
    1.07
     is
    1.07
    Activations Density 0.001%

    No Known Activations