© 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. 254747
    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
    Res
    0.56
    0
    0.53
    あたり
    0.51
    Patient
    0.50
    Reg
    0.50
    Mode
    0.50
    Ref
    0.49
    Protocol
    0.49
    res
    0.48
    Norm
    0.46
    POSITIVE LOGITS
    k
    0.49
     synchron
    0.49
    を有する
    0.48
    كَ
    0.46
     verbunden
    0.46
     recibe
    0.45
     tetrachloride
    0.45
     Shabd
    0.44
    kli
    0.44
    كشن
    0.44
    Activations Density 0.000%

    No Known Activations