© 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. 40-GEMMASCOPE-2-RES-65K
    7. 883
    Prev
    Next
    INDEX
    Explanations

    widely available

    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_40_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
     جوړونکي
    0.49
    GUNDABAD
    0.44
    妛
    0.42
    lensFlare
    0.41
    apuris
    0.41
     ನಾವು
    0.41
    ீரல்
    0.40
    剻
    0.40
    ጠቀም
    0.40
    iftoire
    0.40
    POSITIVE LOGITS
      
    0.56
    4
    0.53
     L
    0.48
    ↵
    0.48
     at
    0.46
    0.46
     P
    0.46
     {
    0.46
     G
    0.45
     /
    0.45
    Activations Density 0.040%

    No Known Activations