© 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. 4624
    Prev
    Next
    INDEX
    Explanations

    assigning variables and values

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

    code returning values

    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
    VSLU
    0.56
    OLYBDENUM
    0.54
     захворю
    0.51
    叁章
    0.49
    PLASMA
    0.48
     انسان
    0.48
    <unused77>
    0.47
    textepsilon
    0.47
     CXCR
    0.47
    Gosudarstvennyj
    0.47
    POSITIVE LOGITS
     this
    0.78
     these
    0.77
     it
    0.69
    this
    0.69
     that
    0.61
     the
    0.60
    new
    0.58
     new
    0.55
    that
    0.55
    .
    0.55
    Activations Density 0.002%

    No Known Activations