© 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. 94122
    Prev
    Next
    INDEX
    Explanations

    early versions or initial states

    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
     MSc
    0.43
    ampaikan
    0.43
     caseload
    0.42
    ParentElement
    0.42
     driveway
    0.41
    anchi
    0.40
    嗯
    0.40
     darken
    0.40
     teacher
    0.39
    车辆
    0.39
    POSITIVE LOGITS
     Somehow
    0.47
     Memorial
    0.44
     Barbados
    0.43
    和
    0.42
    স্ট
    0.42
    ボ
    0.40
    های
    0.40
     Puerto
    0.39
     Smithsonian
    0.39
     Experiments
    0.39
    Activations Density 0.009%

    No Known Activations