© 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. 236722
    Prev
    Next
    INDEX
    Explanations

    low toxicity

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     alternate
    0.43
     workouts
    0.41
    affeine
    0.41
     substituents
    0.41
    ొ
    0.40
     comfortable
    0.40
     serve
    0.40
     subspaces
    0.40
     comparing
    0.40
     create
    0.39
    POSITIVE LOGITS
     erreicht
    0.57
    ιον
    0.54
    板
    0.52
     erforderlich
    0.50
    workItem
    0.48
    ْن
    0.47
    нок
    0.47
     percol
    0.46
    ihu
    0.46
     offenbar
    0.46
    Activations Density 0.001%

    No Known Activations