© 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. 16-GEMMASCOPE-2-RES-65K
    7. 289
    Prev
    Next
    INDEX
    Explanations

    dialogue or internal thoughts

    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_16_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
    at
    0.75
    ing
    0.62
    u
    0.62
    ת
    0.59
    us
    0.58
            
    0.57
    M
    0.55
    er
    0.53
    e
    0.52
    um
    0.51
    POSITIVE LOGITS
     pptd
    0.60
    我
    0.59
    私は
    0.56
    ្នែក
    0.56
     mám
    0.56
    大的
    0.55
    ني
    0.54
     děti
    0.54
     STARTED
    0.53
     pobres
    0.53
    Activations Density 0.054%

    No Known Activations