© 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. 1904
    Prev
    Next
    INDEX
    Explanations

    qualities and topics

    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
     Kuwait
    0.18
    <0x0D>
    0.17
     Arjun
    0.17
     Qt
    0.16
     SIINFEKL
    0.16
     odyssey
    0.15
     Æ
    0.15
     Simba
    0.15
    ?,
    0.15
     Sunny
    0.15
    POSITIVE LOGITS
     enough
    0.21
     demais
    0.21
     về
    0.20
     regarding
    0.20
     درباره
    0.19
     communic
    0.19
     tentang
    0.19
    े
    0.19
    पणे
    0.18
     about
    0.18
    Activations Density 0.767%

    No Known Activations