© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 168326
    Prev
    Next
    INDEX
    Explanations

    REPL-Driven Development

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ;
    0.56
     jednak
    0.49
     לס
    0.49
     ולה
    0.47
     Características
    0.44
     Vanderbilt
    0.44
     וע
    0.43
    ]
    0.43
    transmit
    0.42
     મા
    0.41
    POSITIVE LOGITS
    esecuzione
    0.54
     myopia
    0.50
     correspondences
    0.47
     Treating
    0.47
     Placing
    0.47
     станда
    0.46
    periods
    0.46
     underestimates
    0.45
     inactivity
    0.45
     philosophies
    0.45
    Activations Density 0.002%

    No Known Activations