© 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. 255163
    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
    Issledovatel
    0.46
    ید
    0.46
    Er
    0.44
    PointCloud
    0.44
    ंता
    0.43
    E
    0.43
    Rv
    0.43
    पुर
    0.43
    avano
    0.43
    เผ
    0.43
    POSITIVE LOGITS
     Música
    0.48
    ançois
    0.44
     obscurity
    0.44
     tâches
    0.44
    첩
    0.43
     бассе
    0.43
     ኢን
    0.42
     Grâce
    0.42
     infección
    0.42
     própri
    0.42
    Activations Density 0.001%

    No Known Activations