© 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. 5952
    Prev
    Next
    INDEX
    Explanations

    and in multiple languages

    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
    5
    0.41
    Free
    0.40
    OVER
    0.39
    {
    0.39
    ٥
    0.39
    ０
    0.39
    У
    0.39
    Orientation
    0.38
    س
    0.38
    Advantages
    0.38
    POSITIVE LOGITS
     અને
    0.66
     এবং
    0.60
     आणि
    0.59
     và
    0.57
     ਅਤੇ
    0.55
     και
    0.54
     और
    0.54
     և
    0.53
     and
    0.50
    และ
    0.49
    Activations Density 0.096%

    No Known Activations