© 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. 198067
    Prev
    Next
    INDEX
    Explanations

    numbers and quantities

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

    often reveals

    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
    他
    0.52
    Genome
    0.46
     Relaxation
    0.45
     Genome
    0.44
    genome
    0.44
    她
    0.44
     Genet
    0.44
    城
    0.43
    sé
    0.43
     Concentrate
    0.42
    POSITIVE LOGITS
    =(
    0.59
    htonl
    0.50
     egip
    0.48
     postice
    0.48
    <unused2175>
    0.48
     posticis
    0.48
     juguetes
    0.47
    ți
    0.47
    \"]\
    0.47
    igu
    0.47
    Activations Density 0.001%

    No Known Activations