© 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. 17-GEMMASCOPE-2-RES-16K
    7. 12721
    Prev
    Next
    INDEX
    Explanations

    is to be

    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_17_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
    ahrt
    1.01
     prematurely
    0.95
    ᴀ
    0.94
     Suddenly
    0.94
     isn
    0.93
    NESDAY
    0.93
     অনুভূত
    0.91
    ítez
    0.89
    Suddenly
    0.89
    Something
    0.88
    POSITIVE LOGITS
    再
    0.98
     spost
    0.98
    굶
    0.96
     nech
    0.88
     tutti
    0.87
     stric
    0.87
    聘
    0.86
     lagen
    0.85
     Contr
    0.84
     Chill
    0.83
    Activations Density 0.069%

    No Known Activations