© 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. 139201
    Prev
    Next
    INDEX
    Explanations

    This is

    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
    ಲ್ಲು
    0.42
     Laff
    0.42
     várias
    0.42
    反复
    0.42
    )=
    0.41
     Border
    0.41
     galvanometer
    0.41
     السود
    0.41
    rufen
    0.40
    ණ්
    0.40
    POSITIVE LOGITS
    c
    0.46
     αρχ
    0.42
     σχέ
    0.41
    ούμε
    0.40
    ุ้น
    0.40
     thePack
    0.39
    发生在
    0.39
    itational
    0.39
     aziende
    0.39
     ถึง
    0.39
    Activations Density 0.002%

    No Known Activations