© 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. 175330
    Prev
    Next
    INDEX
    Explanations

    sand and gravel

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

    given the past only one future

    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
    dgs
    0.46
    name
    0.46
    ৬
    0.46
     $((
    0.45
     물
    0.44
         
    0.43
     최고의
    0.43
    maps
    0.42
     역
    0.42
     주로
    0.42
    POSITIVE LOGITS
     diputado
    0.60
     giocatori
    0.57
     jugadores
    0.55
     práctico
    0.54
     comunque
    0.53
     entrenamiento
    0.53
     impuesto
    0.53
     domine
    0.53
     supermerc
    0.52
     nieve
    0.52
    Activations Density 0.000%

    No Known Activations