© 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. 3005
    Prev
    Next
    INDEX
    Explanations

    hyphenated phrases

    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
     -
    -1.23
    ).
    -1.22
     -"
    -1.20
     -.
    -1.13
     $-
    -1.12
     -,
    -1.12
     kleinen
    -1.09
     sicheren
    -1.04
     Grundstück
    -0.99
     blauen
    -0.98
    POSITIVE LOGITS
     yng
    1.16
    。。。。
    1.11
     månader
    1.10
     kuy
    1.05
     måneder
    1.05
     Maroc
    1.04
     ){
    1.03
     høre
    1.03
     regal
    1.02
    和谐
    1.02
    Activations Density 0.034%

    No Known Activations