© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 242786
    Prev
    Next
    INDEX
    Explanations

    custom messaging

    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
     przedmiot
    0.54
    旛
    0.53
    ᡠ
    0.53
    اندان
    0.51
     tarefa
    0.50
     douze
    0.49
     companhia
    0.49
     شرکت
    0.48
    гыз
    0.47
     existência
    0.47
    POSITIVE LOGITS
    s
    0.81
    one
    0.70
    to
    0.64
    on
    0.59
    re
    0.59
    reg
    0.58
    top
    0.57
    rad
    0.57
    S
    0.57
    at
    0.57
    Activations Density 0.001%

    No Known Activations