© 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. 65558
    Prev
    Next
    INDEX
    Explanations

    content and user information

    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
     at
    -1.72
     can
    -1.49
     could
    -1.38
     commonly
    -1.34
     when
    -1.32
    它們
    -1.32
     häufig
    -1.31
     generally
    -1.30
     it
    -1.28
     można
    -1.28
    POSITIVE LOGITS
     you
    3.08
     your
    2.73
     आपको
    1.77
     dessutom
    1.75
     budete
    1.63
     musíte
    1.61
     شما
    1.59
    謦
    1.51
    媄
    1.46
     sizi
    1.45
    Activations Density 0.027%

    No Known Activations