© 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. 16373
    Prev
    Next
    INDEX
    Explanations

    specific countable entities

    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
    -1.00
     första
    -0.92
    eapples
    -0.92
    vesen
    -0.92
    ↵↵↵↵↵↵↵↵↵↵↵
    -0.91
     Gen
    -0.91
    ↵↵
    -0.90
     expected
    -0.87
     först
    -0.86
     oltre
    -0.85
    POSITIVE LOGITS
    individual
    1.69
     individuel
    1.65
     individual
    1.63
     indywidual
    1.55
     individu
    1.51
    Individual
    1.45
     INDIVIDUAL
    1.39
     отдельных
    1.39
     индивидуаль
    1.38
     individually
    1.30
    Activations Density 0.085%

    No Known Activations