© 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. 256821
    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
    Б
    0.50
    तौर
    0.45
    Ｂ
    0.45
     cautious
    0.44
     Conservatives
    0.44
    ካ
    0.44
     distancing
    0.43
    Dangerous
    0.42
    B
    0.42
    cf
    0.42
    POSITIVE LOGITS
     YEAR
    0.52
     제일
    0.50
     나머
    0.47
     culto
    0.46
     월
    0.45
     מו
    0.45
     año
    0.45
    Xd
    0.45
     வினை
    0.44
    año
    0.44
    Activations Density 0.000%

    No Known Activations