© 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. 50505
    Prev
    Next
    INDEX
    Explanations

    legal or forbidden actions

    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
     सुर्खियों
    0.56
     pointless
    0.50
     reminis
    0.48
    ayama
    0.47
    gruntled
    0.47
     hysterical
    0.47
    ٨
    0.46
    помним
    0.46
     clenched
    0.46
    currencies
    0.46
    POSITIVE LOGITS
     SCALE
    0.48
     incorporation
    0.46
    法
    0.45
     installation
    0.44
     resources
    0.44
     enjoyment
    0.43
     economy
    0.43
     extraer
    0.43
    钩
    0.43
    জন
    0.43
    Activations Density 0.002%

    No Known Activations