© 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. 256351
    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
    وی
    0.49
    }:$
    0.49
     enzymatic
    0.48
    سرائيل
    0.48
    ماس
    0.45
     비율
    0.45
    er
    0.44
     adiabatic
    0.44
    දේශ
    0.44
    ட்டை
    0.44
    POSITIVE LOGITS
     Communicate
    0.45
     Rede
    0.44
     !
    0.43
     Writing
    0.43
     Greeting
    0.43
    听
    0.42
    Responding
    0.40
     Suite
    0.40
     Hear
    0.40
     greeting
    0.40
    Activations Density 0.000%

    No Known Activations