© 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. 28577
    Prev
    Next
    INDEX
    Explanations

    . wasn’t / not

    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
     Religion
    0.31
    itabbo
    0.30
    there
    0.28
    asar
    0.28
    следование
    0.28
    现状
    0.27
     هیچ
    0.27
    <0xB2>
    0.27
     Effects
    0.27
    anon
    0.27
    POSITIVE LOGITS
     veya
    0.35
     bzw
    0.34
     oder
    0.32
    หรือ
    0.31
     või
    0.31
     tedy
    0.30
     किंवा
    0.30
     giúp
    0.29
     helps
    0.29
     antibody
    0.29
    Activations Density 0.074%

    No Known Activations