© 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. 34799
    Prev
    Next
    INDEX
    Explanations

    simplified explanations or descriptions

    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
     activeButton
    0.46
     mejorar
    0.45
     quedaría
    0.43
     migliorare
    0.43
     everytime
    0.43
     ghế
    0.42
    ぱ
    0.42
     improvement
    0.42
    itabbam
    0.42
     fome
    0.42
    POSITIVE LOGITS
     sebuah
    0.47
    ENT
    0.44
     அப்ப
    0.43
    IT
    0.43
    mi
    0.42
    мара
    0.42
    코
    0.41
    ма
    0.41
    agers
    0.39
     الجزء
    0.39
    Activations Density 0.003%

    No Known Activations