© 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-65K
    7. 40276
    Prev
    Next
    INDEX
    Explanations

    explaining trends and diagrams conditionally

    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_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
     acrescent
    0.47
     añadir
    0.46
     tambahan
    0.44
     limpiar
    0.42
     empêcher
    0.41
    减轻
    0.41
    膑
    0.41
     Và
    0.41
    收获
    0.41
    远离
    0.41
    POSITIVE LOGITS
    describe
    0.45
    descriptions
    0.44
    ec
    0.43
    ponsorship
    0.43
    el
    0.42
    ied
    0.42
    if
    0.42
    eg
    0.41
    eta
    0.41
    ō
    0.41
    Activations Density 0.039%

    No Known Activations