© 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. 6458
    Prev
    Next
    INDEX
    Explanations

    express plot types, define, booked for you

    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
    விரி
    0.54
    能
    0.54
    浏
    0.53
     голове
    0.50
    虽
    0.50
    ின்ன
    0.46
     изменения
    0.46
    凯
    0.46
    nelles
    0.46
    Ми
    0.46
    POSITIVE LOGITS
    á
    0.47
     cooked
    0.46
    calo
    0.45
    ำ
    0.45
     outsourced
    0.44
    å
    0.42
     outcrop
    0.42
     oligonucle
    0.41
     Highways
    0.40
     ordinance
    0.40
    Activations Density 0.001%

    No Known Activations