© 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
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 2558
    Prev
    Next
    INDEX
    Explanations

    book titles beginning with "The"

    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_262k_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
    /
    1.35
     deste
    1.27
    -
    1.27
    +
    1.22
     and
    1.21
    !
    1.20
     to
    1.19
    ,
    1.17
     or
    1.14
     in
    1.11
    POSITIVE LOGITS
    <unused336>
    1.84
    the
    1.80
    <unused682>
    1.71
     The
    1.70
    <unused1068>
    1.68
    <unused557>
    1.67
    <unused199>
    1.66
    <unused2021>
    1.63
    The
    1.59
    <unused350>
    1.57
    Activations Density 0.005%

    No Known Activations