© 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. 99883
    Prev
    Next
    INDEX
    Explanations

    currently only accept text

    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
    ک
    0.46
    ن
    0.46
    ریان
    0.45
    ﻜ
    0.45
     یا
    0.44
     financière
    0.44
     ERISA
    0.43
     breakage
    0.43
    아
    0.43
    说
    0.43
    POSITIVE LOGITS
    öst
    0.47
    віч
    0.46
    oyen
    0.45
    äng
    0.42
    olverine
    0.42
    aug
    0.42
     genom
    0.42
    apons
    0.41
    andex
    0.41
    irts
    0.40
    Activations Density 0.007%

    No Known Activations