© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 78737
    Prev
    Next
    INDEX
    Explanations

    hidden, emergency, accidents

    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
    <unused688>
    0.43
     arrhythmias
    0.42
    ellow
    0.41
    싯
    0.40
     p
    0.40
     зоны
    0.40
     entornos
    0.39
     ска
    0.39
    hill
    0.39
     ganancias
    0.38
    POSITIVE LOGITS
     multicast
    0.46
     tecnico
    0.46
     unico
    0.46
    의
    0.45
    යින්
    0.45
     serializer
    0.45
     DFA
    0.45
     DNS
    0.44
     millionaire
    0.43
     entrants
    0.43
    Activations Density 0.001%

    No Known Activations