© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 66833
    Prev
    Next
    INDEX
    Explanations

    understanding to

    np_acts-logits-general · gemini-2.5-flash-lite

    multi-stage rockets, fashion, books, clothing, fabrics, zones, BERT

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WING
    0.56
    ZEN
    0.52
    Bedroom
    0.49
     deterrent
    0.48
    <\/
    0.48
     vọng
    0.47
    OO
    0.47
     manure
    0.46
     bushels
    0.46
     caram
    0.46
    POSITIVE LOGITS
    乸
    0.48
     Dos
    0.46
    साल
    0.44
    uchos
    0.44
    𝙠
    0.44
    adeh
    0.43
     saját
    0.43
     Nunca
    0.43
     सभ
    0.42
    entral
    0.42
    Activations Density 0.001%

    No Known Activations