© 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. 123276
    Prev
    Next
    INDEX
    Explanations

    state or condition descriptions

    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
    مپ
    0.47
     აღმასრულებელი
    0.47
    議員
    0.46
     RENDITION
    0.43
    м
    0.43
     verstär
    0.42
    ormous
    0.42
    ᱤ
    0.42
    controllers
    0.42
     fuertes
    0.42
    POSITIVE LOGITS
     vibrational
    0.47
     tissue
    0.45
     उपाय
    0.42
     femmin
    0.42
     spont
    0.41
     special
    0.40
     selfish
    0.40
     특별
    0.40
     sit
    0.40
    Fused
    0.40
    Activations Density 0.003%

    No Known Activations