© 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. 25761
    Prev
    Next
    INDEX
    Explanations

    Python code and SQL

    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
     this
    -1.48
     its
    -1.45
     that
    -1.41
    providedIn
    -1.33
    angkap
    -1.30
     both
    -1.29
     bereits
    -1.27
    قاط
    -1.23
     Both
    -1.23
     from
    -1.21
    POSITIVE LOGITS
    '
    1.21
    ’
    1.19
    *
    1.13
    Importante
    1.13
    Propel
    1.12
     “
    1.11
     afore
    1.10
     consi
    1.08
     dring
    1.07
    ha
    1.06
    Activations Density 0.000%

    No Known Activations