© 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. 155030
    Prev
    Next
    INDEX
    Explanations

    HDR mirrors, CPM systems

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

    Sort of, part of

    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
     imgs
    0.44
    Fear
    0.43
    abre
    0.43
    кугӀ
    0.42
    Fem
    0.42
    Khe
    0.42
    ᶤ
    0.42
    IMAGE
    0.42
    Img
    0.41
    Comparer
    0.41
    POSITIVE LOGITS
    减
    0.47
    一系列
    0.47
     récup
    0.47
    也不会
    0.46
     Schott
    0.45
    该
    0.45
    స్
    0.45
    处理
    0.44
    可能有
    0.44
     bibliographic
    0.44
    Activations Density 0.000%

    No Known Activations