© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 105437
    Prev
    Next
    INDEX
    Explanations

    science and foreign scripts

    np_acts-logits-general · gemini-2.5-flash-lite

    why formula energy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Wasn
    0.48
    en
    0.46
    ós
    0.46
    虽
    0.44
    ခြား
    0.43
     picked
    0.43
     barre
    0.42
    有些
    0.41
    ami
    0.41
    更加
    0.41
    POSITIVE LOGITS
     photosynthesis
    0.51
     photosynthetic
    0.49
    રા
    0.48
     እንቅ
    0.47
     '../../../
    0.46
     കീഴ
    0.46
     সক্র
    0.46
     ابتدائي
    0.46
    ndvi
    0.45
     deforestation
    0.45
    Activations Density 0.000%

    No Known Activations