© 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. 255436
    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
     devaluation
    0.46
    ্মদ
    0.44
    ᱕
    0.43
     embarrassed
    0.42
     frustrating
    0.41
    द्रा
    0.40
     aggravating
    0.40
     loam
    0.40
    entraî
    0.39
     diverted
    0.39
    POSITIVE LOGITS
     което
    0.53
    𝓀
    0.52
     песен
    0.52
    தான்
    0.51
     што
    0.50
     obnov
    0.50
    RAIT
    0.50
    Б
    0.50
     ประก
    0.50
     было
    0.49
    Activations Density 0.001%

    No Known Activations