© 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. 257715
    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
     Cement
    0.45
    نت
    0.44
     Phenomenology
    0.44
    楦
    0.43
    град
    0.43
     Fracture
    0.43
    埝
    0.43
     Dataset
    0.42
    ন
    0.42
    вр
    0.42
    POSITIVE LOGITS
    shooting
    0.52
     gentile
    0.46
     ná
    0.45
    ப்ஸ்
    0.45
    sp
    0.44
    locking
    0.44
    silk
    0.44
    Locked
    0.43
     তেলেভ
    0.43
    Ih
    0.43
    Activations Density 0.001%

    No Known Activations