© 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. 257242
    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
     ሁ
    0.55
    볕
    0.52
     renovación
    0.49
    щены
    0.47
    ᱷ
    0.47
     రెండు
    0.47
     financiación
    0.47
    っくり
    0.46
     구조
    0.46
     motivación
    0.46
    POSITIVE LOGITS
    Z
    0.60
    SCH
    0.50
    Sch
    0.48
    Kevin
    0.46
    ZK
    0.45
    Ari
    0.45
    Sam
    0.45
    Od
    0.45
    Dor
    0.44
    Ish
    0.44
    Activations Density 0.001%

    No Known Activations