© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 43967
    Prev
    Next
    INDEX
    Explanations

    end of sentence

    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_31_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
    私が
    0.42
    AND
    0.40
    Теперь
    0.40
    nested
    0.40
     मैंने
    0.39
    Мне
    0.39
    ѫ
    0.39
    ਫ਼
    0.38
    єте
    0.38
    हमने
    0.38
    POSITIVE LOGITS
     ഇത്
    0.42
    انه
    0.42
     formazione
    0.41
    colorbar
    0.40
    情节
    0.40
     اتفاق
    0.39
    രാഷ്ട്ര
    0.39
     دانش
    0.39
    ثمار
    0.38
     సూపర్
    0.38
    Activations Density 0.000%

    No Known Activations