© 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. 256093
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    water
    0.51
     tones
    0.49
    scene
    0.48
     물
    0.47
    nv
    0.46
    arze
    0.45
    por
    0.45
    pose
    0.45
    cosmos
    0.45
    scenes
    0.44
    POSITIVE LOGITS
     Überg
    0.53
     Adidas
    0.49
     individuo
    0.48
     Tel
    0.47
     Uso
    0.46
     Persön
    0.46
    UBS
    0.45
    J
    0.45
     đứa
    0.44
    أ
    0.44
    Activations Density 0.001%

    No Known Activations