© 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-16K
    7. 2215
    Prev
    Next
    INDEX
    Explanations

    Property definition

    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_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
    Ж
    1.37
    माया
    1.33
    ТУ
    1.31
     військо
    1.30
     batas
    1.28
    COMANDA
    1.26
     जिंदाबाद
    1.23
    꽉
    1.23
    Οι
    1.22
     umožňuje
    1.22
    POSITIVE LOGITS
    '.$
    1.43
     tersebut
    1.32
    。
    1.19
    ）.
    1.15
    然后
    1.14
    $.\\
    1.12
     然后
    1.10
    etera
    1.10
    '.
    1.10
    。...
    1.10
    Activations Density 1.619%

    No Known Activations