© 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-262K
    7. 248385
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     generalised
    0.44
     त्रास
    0.43
    -}$
    0.43
    is
    0.42
    ath
    0.42
    can
    0.42
     abusive
    0.42
    avat
    0.41
     telesc
    0.41
    sters
    0.41
    POSITIVE LOGITS
    现在
    0.43
    此时
    0.43
    どんな
    0.42
    UO
    0.42
    证据
    0.41
    ンダー
    0.41
     currentState
    0.41
    璜
    0.40
     evidence
    0.40
     некоторы
    0.39
    Activations Density 0.006%

    No Known Activations