© 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-262K
    7. 112160
    Prev
    Next
    INDEX
    Explanations

    understanding abstract concepts and reasoning

    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
    *
    0.45
    Quant
    0.43
    স্ত
    0.39
     ida
    0.39
    Staff
    0.39
    免费
    0.39
    со
    0.39
    名为
    0.38
    为了
    0.38
    Additive
    0.38
    POSITIVE LOGITS
    regulate
    0.55
     wry
    0.48
     impuls
    0.47
     സംഭവ
    0.47
     activación
    0.46
    戾
    0.46
    driving
    0.46
     amplify
    0.45
    nections
    0.45
     engage
    0.44
    Activations Density 0.002%

    No Known Activations