© 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. 2555
    Prev
    Next
    INDEX
    Explanations

    prepositions like on

    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
    िक्रमा
    1.53
    nement
    1.51
    _{
    1.44
    ^{*
    1.43
    _{\
    1.37
    റേ
    1.36
    ^{(
    1.26
     pretence
    1.22
    ದಗ
    1.20
     behalf
    1.20
    POSITIVE LOGITS
    s
    2.11
     mendatang
    1.64
    at
    1.63
    сь
    1.53
    sack
    1.52
     afar
    1.52
    नांतर
    1.51
    या
    1.49
    o
    1.48
    ्स
    1.48
    Activations Density 0.005%

    No Known Activations