© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-16K
    4. 13584
    Prev
    Next
    INDEX
    Explanations

    eyes looking down or away

    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_16k_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
    鍋
    0.45
    Cancelar
    0.44
     Аль
    0.44
     мони
    0.44
     엔
    0.44
    िश्च
    0.43
     चाय
    0.43
    猞
    0.43
    нется
    0.42
    alamat
    0.42
    POSITIVE LOGITS
     Blind
    0.50
     Sens
    0.47
     sens
    0.46
     blind
    0.45
     fortune
    0.42
     आर्थिक
    0.40
     econom
    0.39
     Aud
    0.39
    Sens
    0.39
     Vox
    0.39
    Activations Density 0.087%

    No Known Activations