© 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-3-12B-IT
    5. 24-GEMMASCOPE-2-RES-16K
    7. 2971
    Prev
    Next
    INDEX
    Explanations

    fact, actually

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_24_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
    s
    1.01
    ir
    0.97
    il
    0.96
    k
    0.93
    ut
    0.88
     ×
    0.85
    ures
    0.84
    ></
    0.84
    ין
    0.84
    im
    0.81
    POSITIVE LOGITS
     tatsächlich
    1.38
    いた
    1.22
     sebenarnya
    1.20
     एक्चुअली
    1.13
    并未
    1.10
     scritto
    1.09
    むしろ
    1.09
    たっぷり
    1.07
    Actually
    1.06
     실제로
    1.06
    Activations Density 0.016%

    No Known Activations