© 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. 259568
    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
     करते
    0.44
    ándole
    0.44
     ï
    0.42
    ándolo
    0.42
    нете
    0.41
     vari
    0.40
     restraints
    0.40
    apay
    0.40
     एपी
    0.40
    ज़ा
    0.39
    POSITIVE LOGITS
    স্বর
    0.49
    ˍ
    0.47
     Funktionen
    0.47
    excerpt
    0.46
    K
    0.46
    ল
    0.46
    Mats
    0.46
    まし
    0.46
     pylori
    0.45
     ஒன்றிய
    0.44
    Activations Density 0.000%

    No Known Activations