© 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. 41340
    Prev
    Next
    INDEX
    Explanations

    If you add

    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
    ananti
    0.50
    ſs
    0.50
    ிலான
    0.50
    榱
    0.50
    विष्ट
    0.47
    განი
    0.47
    της
    0.46
    enderita
    0.46
    膯
    0.46
    acı
    0.46
    POSITIVE LOGITS
    );
    0.57
    ↵
    0.53
    ↵↵
    0.53
     c
    0.49
     container
    0.49
    "
    0.49
     dips
    0.48
     tem
    0.48
     purposes
    0.48
    _
    0.47
    Activations Density 0.002%

    No Known Activations