© 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. 233529
    Prev
    Next
    INDEX
    Explanations

    and/or

    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
     RS
    0.47
     OTC
    0.44
    淇
    0.43
     BTC
    0.43
     BC
    0.42
     reset
    0.42
     ACCESS
    0.42
     TICK
    0.42
    ン
    0.42
     BG
    0.41
    POSITIVE LOGITS
     κατο
    0.50
     concealing
    0.47
     και
    0.47
     страну
    0.46
     deixando
    0.46
     پوش
    0.46
     encontr
    0.46
     đeo
    0.46
     కల
    0.45
    hadas
    0.44
    Activations Density 0.001%

    No Known Activations