© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 111462
    Prev
    Next
    INDEX
    Explanations

    immediate actions or options

    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
     artistas
    0.49
     давайте
    0.44
     periodistas
    0.44
    tStart
    0.44
    
    0.44
    ティ
    0.43
     ফিল্ম
    0.43
     Crisp
    0.41
    ક્ર
    0.41
    ॉर्क
    0.41
    POSITIVE LOGITS
    STEIN
    0.47
    1
    0.47
    D
    0.46
    K
    0.46
    вания
    0.46
    DIM
    0.46
    Hamm
    0.46
    2
    0.45
    력
    0.45
    SA
    0.44
    Activations Density 0.003%

    No Known Activations