© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 93862
    Prev
    Next
    INDEX
    Explanations

    setting boundaries

    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
    volvement
    0.52
    榃
    0.48
     unpopular
    0.46
     Involvement
    0.46
     pendapat
    0.45
    innah
    0.45
    ℅
    0.45
    ukkig
    0.44
    喹
    0.44
    Senior
    0.44
    POSITIVE LOGITS
     nozzles
    0.61
     machining
    0.59
     prismatic
    0.59
     acciaio
    0.59
     welded
    0.58
     vertically
    0.55
     machined
    0.55
     ceramic
    0.54
     recyclable
    0.54
     thermoplastic
    0.54
    Activations Density 0.011%

    No Known Activations