Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 35277
    Prev
    Next
    INDEX
    Explanations

    beyond specifics

    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
    奂
    0.51
    𝕥
    0.48
    指導
    0.47
    тен
    0.46
    תה
    0.46
     prakty
    0.45
     кіль
    0.44
     jedn
    0.44
     instrucción
    0.44
     吃
    0.43
    POSITIVE LOGITS
     dairy
    0.44
    ulosic
    0.44
    7
    0.44
    8
    0.44
    ausible
    0.43
    asan
    0.42
     belonging
    0.42
    6
    0.41
     coexistence
    0.41
    "
    0.41
    Activations Density 0.001%

    No Known Activations