© 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. 32635
    Prev
    Next
    INDEX
    Explanations

    code strings and general text

    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
     vestido
    0.43
     layering
    0.42
     శక్తి
    0.41
     shortcut
    0.41
    up
    0.41
    大幅
    0.41
    upo
    0.40
    u
    0.40
     shrub
    0.40
    esh
    0.39
    POSITIVE LOGITS
    นั้น
    0.48
    inée
    0.46
                     
    0.45
    According
    0.44
     notificações
    0.43
     ہوگا
    0.43
                      
    0.43
    <<<<
    0.42
    \
    0.41
    Пре
    0.41
    Activations Density 0.004%

    No Known Activations