© 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. 50322
    Prev
    Next
    INDEX
    Explanations

    AI and human understanding

    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
    栨
    0.47
    峮
    0.44
     🤔
    0.44
     turb
    0.43
    unct
    0.43
     Politics
    0.42
     Defense
    0.42
     Healthy
    0.41
    atrice
    0.41
     getNode
    0.41
    POSITIVE LOGITS
    ouverture
    0.45
    ারা
    0.45
     उद्
    0.45
    ุ
    0.45
    branco
    0.44
    data
    0.43
     αρ
    0.42
    categoria
    0.42
    lvl
    0.42
    gua
    0.42
    Activations Density 0.003%

    No Known Activations