© 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-3-12B-IT
    5. 24-GEMMASCOPE-2-RES-16K
    7. 4672
    Prev
    Next
    INDEX
    Explanations

    starts a phrase or clause

    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
     Tattha
    0.64
    UWORD
    0.61
     Спорттук
    0.58
    䔬
    0.55
     Fleurit
    0.55
    <0xEB>
    0.54
    ingi
    0.54
    Cadastro
    0.54
    INCLUDING
    0.53
    Parameterized
    0.53
    POSITIVE LOGITS
     (
    0.70
    .
    0.61
    さんの
    0.60
     =
    0.60
    <0xE2>
    0.57
     fascism
    0.57
     evitare
    0.57
     ini
    0.57
     fondée
    0.56
     என்பத
    0.55
    Activations Density 0.152%

    No Known Activations