© 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. 132708
    Prev
    Next
    INDEX
    Explanations

    replaced about

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

    zero-shot learning

    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
    健康
    0.54
    未来
    0.53
    चार्ज
    0.52
    லீ
    0.49
    埂
    0.49
     Shree
    0.48
    文化的
    0.47
     නිෂ්
    0.47
    ULTURE
    0.46
     aggravate
    0.45
    POSITIVE LOGITS
     nariz
    0.46
     isopropyl
    0.45
     payloads
    0.45
     priors
    0.44
     dere
    0.43
    iare
    0.43
    ্লাহ
    0.42
     lymphocytic
    0.42
     collected
    0.41
    :
    0.41
    Activations Density 0.001%

    No Known Activations