© 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. 109531
    Prev
    Next
    INDEX
    Explanations

    3D scanners, lever, research areas

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

    challenge facing, actual diameter, hot rolling, can adjust

    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
     sirf
    0.46
     Layout
    0.45
     Veget
    0.45
    SI
    0.44
    TeX
    0.43
    perceptron
    0.43
    warehouse
    0.42
    ၻ
    0.42
     conoscenza
    0.42
     Catalunya
    0.42
    POSITIVE LOGITS
    eurs
    0.47
    稳定的
    0.46
    ividade
    0.44
    িশালী
    0.43
    败
    0.42
     적
    0.41
    olge
    0.41
    ப்போதும்
    0.40
    erende
    0.40
    lado
    0.40
    Activations Density 0.001%

    No Known Activations