© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 5072
    Prev
    Next
    INDEX
    Explanations

    numbers and foreign words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     (£
    1.28
     ▸
    1.24
     >;
    1.19
    捱
    1.18
     criticise
    1.18
     Palmer
    1.18
    heb
    1.17
    
    1.16
     perils
    1.14
     despatch
    1.13
    POSITIVE LOGITS
    راضي
    1.35
    6
    1.27
    8
    1.20
    ٦
    1.15
     стоя
    1.13
     зелены
    1.12
    4
    1.12
    Yellow
    1.10
    ٨
    1.08
    yellow
    1.05
    Activations Density 0.057%

    No Known Activations