© 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. 139007
    Prev
    Next
    INDEX
    Explanations

    small sizes of physical objects and models

    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
     שנ
    0.51
     prohibitions
    0.49
     absences
    0.48
     QuantityOnHand
    0.45
     avocados
    0.45
    䂝
    0.45
    acées
    0.45
     monies
    0.45
     lineages
    0.44
    डक्शन
    0.44
    POSITIVE LOGITS
    communicate
    0.52
    Electrical
    0.49
    Parent
    0.48
    Executor
    0.47
    cable
    0.47
    ی
    0.47
    end
    0.46
    ַ
    0.46
    evaluate
    0.46
    mother
    0.46
    Activations Density 0.005%

    No Known Activations