© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 50633
    Prev
    Next
    INDEX
    Explanations

    abstract concepts in multiple languages

    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
    Util
    0.49
    away
    0.43
     captivity
    0.43
    CAMP
    0.42
    Away
    0.42
    I
    0.42
     camping
    0.41
     chickens
    0.41
     camper
    0.41
    INE
    0.40
    POSITIVE LOGITS
    하거나
    0.51
    脸色
    0.50
     Nietzsche
    0.44
    ╾
    0.44
     અથવા
    0.44
    あえず
    0.43
    ักษณ์
    0.43
     Atau
    0.42
    缤
    0.42
     acquaintances
    0.41
    Activations Density 0.025%

    No Known Activations