© 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. 138648
    Prev
    Next
    INDEX
    Explanations

    describing qualities or states

    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
    ки
    0.51
     ತು
    0.48
     入れ
    0.48
    كة
    0.47
    ccedil
    0.47
     oreille
    0.46
     耳
    0.46
     inégal
    0.45
    뷊
    0.45
    }_{
    0.45
    POSITIVE LOGITS
    Configurations
    0.40
    мулятор
    0.40
    Dummy
    0.39
    Modal
    0.39
    ing
    0.38
    Visualization
    0.37
    LinkedList
    0.37
    Behaviours
    0.37
    Sou
    0.37
    ویان
    0.37
    Activations Density 0.001%

    No Known Activations