© 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. 90054
    Prev
    Next
    INDEX
    Explanations

    Bible verses about Stars

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

    complex process breakdown nuanced details

    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
     mise
    0.52
     reproduce
    0.50
     plek
    0.46
     parcela
    0.46
     choisi
    0.46
     usare
    0.46
    я
    0.46
     questa
    0.45
     disegno
    0.45
     sorella
    0.44
    POSITIVE LOGITS
    culoskeletal
    0.49
    stechnik
    0.46
     UK
    0.46
    sov
    0.45
    SAA
    0.44
    çuk
    0.44
    UK
    0.43
    giene
    0.43
     NAA
    0.43
    嘤
    0.42
    Activations Density 0.001%

    No Known Activations