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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 26030
    Prev
    Next
    INDEX
    Explanations

    food consumption, arbitrary, spectrum

    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
    0.55
    unico
    0.45
    私の
    0.43
     догово
    0.42
     sadece
    0.42
     ನನಗೆ
    0.41
    インター
    0.41
    ｀
    0.41
    フォード
    0.40
     শুধু
    0.40
    POSITIVE LOGITS
     Ventilation
    0.45
     Hygiene
    0.45
     Consciousness
    0.45
     och
    0.44
    และการ
    0.43
     Massive
    0.42
     dichotom
    0.42
     Boud
    0.42
     ventilation
    0.42
    okine
    0.42
    Activations Density 0.023%

    No Known Activations