© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 81973
    Prev
    Next
    INDEX
    Explanations

    sensory descriptions and purpose

    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
     sensibilities
    0.49
    ک
    0.44
     fungus
    0.43
    inne
    0.43
    yang
    0.42
     Amanda
    0.41
    гле
    0.40
     egregious
    0.40
     caudal
    0.39
     carbide
    0.39
    POSITIVE LOGITS
    锂
    0.46
     స్
    0.45
    墺
    0.45
     到
    0.44
    角色
    0.44
     транспорт
    0.43
     Vod
    0.43
    䩕
    0.43
     单
    0.42
     közel
    0.42
    Activations Density 0.006%

    No Known Activations