© 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. 71904
    Prev
    Next
    INDEX
    Explanations

    agent, character, wield followed by punctuation

    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
    品種
    0.52
    将
    0.48
    ▶
    0.46
     с
    0.45
    Invite
    0.44
    range
    0.43
    selector
    0.42
    explorer
    0.42
    ให้
    0.42
    ►
    0.42
    POSITIVE LOGITS
     ersche
    0.52
    aba
    0.51
    ataa
    0.49
     wygl
    0.48
    ashing
    0.47
    aking
    0.46
     restauration
    0.46
    òng
    0.45
    orul
    0.45
    ospod
    0.45
    Activations Density 0.008%

    No Known Activations