© 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-262K
    7. 394
    Prev
    Next
    INDEX
    Explanations

    and followed by verbs

    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_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
    aren
    0.50
    4
    0.50
    ator
    0.48
    ord
    0.47
    ian
    0.47
    ely
    0.47
    were
    0.47
    ido
    0.46
    ali
    0.46
    5
    0.46
    POSITIVE LOGITS
    \
    0.57
    ަ
    0.49
     on
    0.47
    િ
    0.47
    </h3>
    0.44
    شك
    0.43
     orbits
    0.43
     NUS
    0.43
     OPS
    0.40
     USS
    0.39
    Activations Density 0.267%

    No Known Activations