© 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. 16-GEMMASCOPE-2-RES-262K
    7. 45908
    Prev
    Next
    INDEX
    Explanations

    cash, document, work, story, reel

    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_16_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
    ier
    0.58
    ent
    0.57
    m
    0.57
    c
    0.55
    n
    0.54
    p
    0.53
    ain
    0.53
    ia
    0.51
     n
    0.50
     an
    0.50
    POSITIVE LOGITS
    OPTV
    0.53
     Tenemos
    0.51
     சிகி
    0.49
    䣮
    0.49
     الهمزه
    0.48
     démar
    0.48
     distraught
    0.47
     Prothorax
    0.47
     Chayin
    0.47
    使う
    0.46
    Activations Density 0.000%

    No Known Activations