© 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. 39909
    Prev
    Next
    INDEX
    Explanations

    of followed by noun phrase

    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
     with
    -2.34
     these
    -2.25
     during
    -2.14
     before
    -2.09
     every
    -2.08
     using
    -2.06
     regarding
    -2.06
     after
    -2.06
     sizable
    -2.05
     began
    -2.03
    POSITIVE LOGITS
     wacky
    2.50
     blatant
    2.48
     AMAZING
    2.41
     REALLY
    2.36
    咈
    2.34
    蹰
    2.33
     VERY
    2.33
     molti
    2.31
     ferocious
    2.31
     créer
    2.28
    Activations Density 0.051%

    No Known Activations