© 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. 53-GEMMASCOPE-2-RES-262K
    4. 35414
    Prev
    Next
    INDEX
    Explanations

    baselines, BASICS, lift

    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_53_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
     baseline
    1.03
     Baseline
    0.93
    baseline
    0.89
    Baseline
    0.88
    BASELINE
    0.72
     линий
    0.45
     линии
    0.42
    龺
    0.40
    oga
    0.40
     stretching
    0.40
    POSITIVE LOGITS
    illes
    0.43
    undos
    0.41
    elles
    0.40
    kates
    0.39
    HEADERS
    0.39
    ICLES
    0.38
    HttpSession
    0.38
    Wings
    0.38
     antigos
    0.38
     intensely
    0.38
    Activations Density 0.001%

    No Known Activations