© 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-3-12B-IT
    5. 24-GEMMASCOPE-2-RES-262K
    7. 12788
    Prev
    Next
    INDEX
    Explanations

    leads to outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_24_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    :
    0.95
    স্তাফ
    0.90
    سری
    0.81
    بازی
    0.81
    c
    0.81
    मधील
    0.80
    dari
    0.80
     ketika
    0.79
    স্তাফিজ
    0.79
    Dieser
    0.79
    POSITIVE LOGITS
     عدم
    1.13
    siniz
    1.09
     postponement
    1.03
     discontinuation
    1.02
     появ
    0.97
     dissatisfaction
    0.96
     shortages
    0.96
    ﺨ
    0.96
     sleepless
    0.95
     frustrations
    0.94
    Activations Density 0.003%

    No Known Activations