© 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. 11091
    Prev
    Next
    INDEX
    Explanations

    those followed by noun or LLC followed by parenthesis

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

    avoiding unwanted artifacts

    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
    、
    0.52
    王
    0.49
    ião
    0.48
    定
    0.46
    。
    0.45
    必ず
    0.44
    及
    0.44
    적
    0.44
    веря
    0.44
    веро
    0.43
    POSITIVE LOGITS
     Jawa
    0.53
     Ayam
    0.52
     Aal
    0.52
     स्लाइड
    0.51
     malo
    0.50
     આવ
    0.50
    hips
    0.50
     Guns
    0.48
     lézards
    0.48
     pravi
    0.48
    Activations Density 0.000%

    No Known Activations