© 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-65K
    7. 10965
    Prev
    Next
    INDEX
    Explanations

    all other

    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_65k_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
     ಎರಡು
    0.43
     ორი
    0.43
    ﺗ
    0.43
     দুটি
    0.43
     двумя
    0.43
     addirittura
    0.42
    ელი
    0.41
    ﺃ
    0.40
     দুটো
    0.40
    दोनों
    0.39
    POSITIVE LOGITS
     other
    1.53
    以外の
    1.47
     autres
    1.38
     других
    1.35
     અન્ય
    1.31
     otras
    1.30
     अन्य
    1.28
     інших
    1.27
     অন্যান্য
    1.27
     इतर
    1.27
    Activations Density 0.499%

    No Known Activations