© 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. 22-GEMMASCOPE-RES-131K
    7. 26234
    Prev
    Next
    INDEX
    Explanations

    sentence beginnings with question words

    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_22/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
     where
    -1.47
     this
    -1.45
     other
    -1.42
     which
    -1.29
     at
    -1.25
     as
    -1.23
     all
    -1.23
     or
    -1.18
     our
    -1.08
     on
    -1.07
    POSITIVE LOGITS
    ܆
    1.18
     refroid
    1.16
     remplacer
    1.12
     estrema
    1.11
     diminuer
    1.10
     équip
    1.09
    也非常
    1.09
    should
    1.09
     envoyer
    1.08
     terminer
    1.08
    Activations Density 0.006%

    No Known Activations