© 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. 29-GEMMASCOPE-2-RES-16K
    7. 3486
    Prev
    Next
    INDEX
    Explanations

    press keys

    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_29_width_16k_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
     bronchitis
    0.69
     déploy
    0.68
    পরি
    0.66
    秩
    0.64
    彭
    0.64
     Domain
    0.64
     parquet
    0.64
     აღმასრულებელი
    0.63
    堺
    0.63
     বলিয়
    0.63
    POSITIVE LOGITS
     keyboard
    2.83
     Keyboard
    2.63
    Keyboard
    2.56
     keyboards
    2.51
    keyboard
    2.36
    键盘
    2.30
     teclado
    2.21
     keys
    2.15
     клавиа
    2.14
     keyst
    2.10
    Activations Density 0.370%

    No Known Activations