© 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. 174901
    Prev
    Next
    INDEX
    Explanations

    rightvibrationpositioned

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

    predictive maintenance

    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
     (@
    0.50
     confining
    0.46
     alk
    0.45
     physically
    0.45
    CHECK
    0.44
     hv
    0.42
    कारी
    0.42
     que
    0.41
    <eos>
    0.41
     vinyl
    0.41
    POSITIVE LOGITS
    parametri
    0.55
     zusätz
    0.52
     параметры
    0.48
    razione
    0.47
    inib
    0.46
     පරි
    0.46
    莨
    0.46
    terrorism
    0.46
     prendere
    0.44
    
    0.44
    Activations Density 0.001%

    No Known Activations