© 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. 247258
    Prev
    Next
    INDEX
    Explanations

    railway Museum

    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
     bosom
    0.48
     catechol
    0.47
     synergy
    0.46
    劻
    0.46
    Quel
    0.46
     cauldron
    0.46
     pomegranate
    0.45
    зации
    0.45
     potentiometer
    0.44
     catastrophes
    0.44
    POSITIVE LOGITS
    traf
    0.57
     î
    0.55
    k
    0.55
     Hạ
    0.54
    r
    0.53
     tịch
    0.52
    vah
    0.50
    raines
    0.49
    lant
    0.49
     într
    0.48
    Activations Density 0.000%

    No Known Activations