© 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. 10623
    Prev
    Next
    INDEX
    Explanations

    generate and classify

    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
     permutation
    0.48
    זו
    0.47
     ar
    0.46
    ن
    0.46
     Vibration
    0.46
     Fusion
    0.46
    ಣಿ
    0.45
     tango
    0.45
     suits
    0.45
     arra
    0.45
    POSITIVE LOGITS
     तात्पर्य
    0.41
     beneficios
    0.41
     फरार
    0.40
    Apl
    0.38
     vše
    0.38
    勍
    0.38
     یور
    0.38
     grassy
    0.38
    癶
    0.38
    benefits
    0.37
    Activations Density 0.005%

    No Known Activations