© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 7971
    Prev
    Next
    INDEX
    Explanations

    feature column in tables

    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
     semantics
    1.06
    trivial
    1.04
    aarr
    0.95
     pérdidas
    0.94
    o
    0.93
    terrorism
    0.93
     tmux
    0.92
    quinolin
    0.92
    éricos
    0.91
     иных
    0.90
    POSITIVE LOGITS
    Ᏻ
    0.96
     zou
    0.88
     scaffolding
    0.86
    盤
    0.84
     operasi
    0.82
     Gegensatz
    0.82
    ंना
    0.82
     गणपति
    0.82
     cięż
    0.81
    מוש
    0.81
    Activations Density 0.034%

    No Known Activations