© 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. 76368
    Prev
    Next
    INDEX
    Explanations

    review at your convenience

    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
     صور
    0.44
     சாத
    0.44
     箱
    0.43
     concluded
    0.42
     Savannah
    0.42
    faction
    0.41
     concluding
    0.41
    nd
    0.41
     contral
    0.40
     Rhode
    0.40
    POSITIVE LOGITS
    ᱟ
    0.53
     эшлә
    0.49
    áln
    0.49
     предоставляет
    0.46
     iterable
    0.45
    ాలపై
    0.45
     infraestructura
    0.45
     பேராசிரியர்
    0.44
     embe
    0.44
     sicuramente
    0.44
    Activations Density 0.003%

    No Known Activations