© 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. 13608
    Prev
    Next
    INDEX
    Explanations

    specific 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
    ;//
    0.30
    
    0.30
    (.*
    0.30
    
    0.28
    বাদিক
    0.27
     информации
    0.27
    মনের
    0.27
    }/>
    0.27
    -__
    0.26
     למ
    0.26
    POSITIVE LOGITS
     be
    0.34
    ة
    0.32
    0.32
    ن
    0.32
     أ
    0.30
     که
    0.30
    那样
    0.30
     że
    0.30
     där
    0.29
    ین
    0.29
    Activations Density 0.296%

    No Known Activations