© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 220322
    Prev
    Next
    INDEX
    Explanations

    1 point answers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ądź
    0.41
    ｻ
    0.40
    سپ
    0.38
     gorgeous
    0.38
     ще
    0.37
     pén
    0.37
    Transient
    0.37
    ៤
    0.36
     بم
    0.36
    ૩
    0.36
    POSITIVE LOGITS
     zéro
    0.39
     emberek
    0.38
    ras
    0.37
     concord
    0.37
     शास्त्रों
    0.36
     ľudí
    0.36
    人は
    0.35
    yler
    0.35
     expliqué
    0.35
     जीरो
    0.35
    Activations Density 0.001%

    No Known Activations