© 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. 240750
    Prev
    Next
    INDEX
    Explanations

    text associated with dates

    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
     enables
    0.63
     allows
    0.57
     a
    0.55
     consente
    0.52
     facilitates
    0.50
     NY
    0.49
     unequ
    0.48
     makes
    0.47
     Wi
    0.47
     attaches
    0.47
    POSITIVE LOGITS
    periode
    0.44
    catenin
    0.44
    sentiment
    0.43
    諫
    0.43
    helix
    0.43
    suggestion
    0.42
    centric
    0.42
    butanol
    0.41
    timedelta
    0.41
    period
    0.40
    Activations Density 0.001%

    No Known Activations