© 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-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 9988
    Prev
    Next
    INDEX
    Explanations

    individual plus specific noun/adjective

    np_acts-logits-general · gemini-2.5-flash-lite

    individual rights, merit, freedom

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_40_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ↵↵
    0.56
    เตอร์
    0.50
     a
    0.50
     ออก
    0.49
     south
    0.48
    라운
    0.48
    ͡
    0.46
    📘
    0.46
     sır
    0.46
    व
    0.46
    POSITIVE LOGITS
     индивидуа
    0.80
    individu
    0.78
     individ
    0.75
     индиви
    0.73
    individ
    0.73
     individus
    0.73
     Individ
    0.70
    istic
    0.70
     individuos
    0.70
     Individual
    0.68
    Activations Density 0.043%

    No Known Activations