© 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. 12-GEMMASCOPE-2-RES-16K
    7. 15927
    Prev
    Next
    INDEX
    Explanations

    go out

    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_12_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
    ست
    1.37
    <0xAD>
    1.25
     takers
    1.23
     contractions
    1.23
     ganglions
    1.23
     defamation
    1.22
     savages
    1.20
     Voraussetzungen
    1.20
    ^+,
    1.18
     langues
    1.17
    POSITIVE LOGITS
    an
    1.38
     empe
    1.14
     aé
    1.09
    a
    1.09
     ось
    1.08
    ีน
    1.04
    ../
    1.01
    of
    0.99
     früh
    0.99
    with
    0.98
    Activations Density 0.020%

    No Known Activations