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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 65525
    Prev
    Next
    INDEX
    Explanations

    categories and information breakdown

    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_65k_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
    ada
    0.50
    ાસ
    0.49
     anthropology
    0.45
    ologico
    0.44
     dilated
    0.44
    ayer
    0.43
    𝓊
    0.43
    Kemudian
    0.42
    upe
    0.42
    ('_
    0.42
    POSITIVE LOGITS
     Football
    0.55
     delivers
    0.52
     Categories
    0.52
     Communications
    0.51
     Soccer
    0.51
     Performs
    0.51
     Sales
    0.50
     Classification
    0.50
     Sprach
    0.50
     Spezial
    0.50
    Activations Density 0.037%

    No Known Activations