© 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. 134586
    Prev
    Next
    INDEX
    Explanations

    xaxis title, tick, color, angle

    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
    Indigo
    0.43
    中午
    0.38
     Bosco
    0.38
    ATOM
    0.38
    CharAt
    0.38
     बुनिया
    0.37
    Heart
    0.37
    汉
    0.37
    Concern
    0.37
     زخم
    0.37
    POSITIVE LOGITS
    pad
    0.50
    xref
    0.45
    árm
    0.43
     Pad
    0.42
    bgcolor
    0.40
     bgcolor
    0.40
     Pape
    0.40
     xref
    0.39
     referencing
    0.39
    famil
    0.39
    Activations Density 0.001%

    No Known Activations