© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 84622
    Prev
    Next
    INDEX
    Explanations

    **Peach**, teaching, Abrechnung

    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
    .[/
    0.38
    .]
    0.37
    .”
    0.37
    ειας
    0.37
    ቦች
    0.36
     exclusively
    0.36
     esclusivamente
    0.36
    िसिटी
    0.36
     mulheres
    0.36
     zerstört
    0.35
    POSITIVE LOGITS
     অনুযায়ী
    0.47
    とりあえず
    0.46
     primi
    0.45
     довольно
    0.44
     기준으로
    0.43
     +
    0.42
     good
    0.42
     достаточно
    0.42
     punya
    0.42
    好的
    0.41
    Activations Density 0.018%

    No Known Activations