© 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. 227969
    Prev
    Next
    INDEX
    Explanations

    chemical applications

    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
    弐
    0.48
    率は
    0.46
    트는
    0.45
    followfollow
    0.43
     Dac
    0.43
    flashlight
    0.42
    平面
    0.42
    elementProp
    0.42
    รวจ
    0.41
     telescopic
    0.41
    POSITIVE LOGITS
    Necess
    0.44
     insights
    0.44
    arı
    0.43
     өт
    0.43
    -
    0.43
    。
    0.43
    ोर
    0.42
    '
    0.42
     hinzuge
    0.41
     yaklaş
    0.41
    Activations Density 0.001%

    No Known Activations