© 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. 40-GEMMASCOPE-2-RES-262K
    7. 134177
    Prev
    Next
    INDEX
    Explanations

    in or im prefix

    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_40_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
    េច
    0.42
     weakness
    0.40
     freely
    0.40
    ariski
    0.40
     مضبوط
    0.40
    weak
    0.38
    ティア
    0.38
    /"
    0.38
     nk
    0.38
    ༎
    0.38
    POSITIVE LOGITS
     lluvia
    0.45
     Unusual
    0.44
     เดือน
    0.40
     giugno
    0.40
     iunie
    0.40
    ater
    0.39
    cluso
    0.39
     alcanzar
    0.38
     identificación
    0.38
     laguna
    0.38
    Activations Density 0.025%

    No Known Activations