© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 11304
    Prev
    Next
    INDEX
    Explanations

    growth and development

    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_12_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
     Olaf
    1.12
     Фі
    1.05
    v
    1.04
     sugars
    1.02
     Dateien
    1.02
     Novgorod
    1.01
    emura
    1.01
     Fär
    1.01
     Macau
    1.00
     Canadá
    1.00
    POSITIVE LOGITS
    ی
    1.35
    ה
    1.35
    া
    1.20
    на
    1.07
    их
    1.03
     improvement
    1.02
    ក្ខ
    1.02
     learning
    1.01
     novice
    0.95
    ление
    0.95
    Activations Density 0.142%

    No Known Activations