© 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. 72512
    Prev
    Next
    INDEX
    Explanations

    the way to

    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
     its
    -1.88
     XXXVII
    -1.46
     XXXIV
    -1.46
    
    -1.41
     XXVII
    -1.39
     XXVIII
    -1.39
     desnuda
    -1.38
     XXXII
    -1.36
    ⸰
    -1.36
    ᠷ
    -1.35
    POSITIVE LOGITS
     is
    3.16
     was
    2.05
    Your
    1.61
     goal
    1.54
     must
    1.52
     requirement
    1.52
     of
    1.52
     should
    1.51
     thing
    1.42
     needs
    1.41
    Activations Density 0.618%

    No Known Activations