© 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. 231641
    Prev
    Next
    INDEX
    Explanations

    some possible

    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
     onDelete
    0.45
    เล็ก
    0.42
    TreeNavigator
    0.41
    ᄀ
    0.41
     getN
    0.41
     přímo
    0.40
    кина
    0.40
    িনা
    0.40
     Theology
    0.40
    ATIONAL
    0.40
    POSITIVE LOGITS
     apropri
    0.51
     aplic
    0.49
     arrib
    0.49
     aplicaciones
    0.48
    t
    0.48
     ugu
    0.47
     unsettling
    0.46
    hig
    0.46
     equivalente
    0.45
     disponibilidade
    0.45
    Activations Density 0.000%

    No Known Activations