© 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-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 11666
    Prev
    Next
    INDEX
    Explanations

    Eiffel tower

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_9_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
     mezzanine
    1.59
    𝑻
    1.42
     adquir
    1.40
     FIB
    1.34
    ॓
    1.27
    ve
    1.26
     Playoffs
    1.26
     lucrat
    1.26
     conservación
    1.25
     episcop
    1.25
    POSITIVE LOGITS
    최
    1.17
    ه
    1.15
    ו
    1.13
    ساز
    1.12
     localObject
    1.10
     از
    1.07
     არა
    1.06
    뚜
    1.06
    說
    1.06
    從
    1.06
    Activations Density 0.000%

    No Known Activations