© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 222654
    Prev
    Next
    INDEX
    Explanations

    lists of foreign words and themes

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

    holding (state)

    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
    ํ
    0.50
     upregulation
    0.48
    ボル
    0.46
    품
    0.46
    레
    0.45
    นะนำ
    0.45
    령
    0.45
    은
    0.44
    یه
    0.44
    댈
    0.44
    POSITIVE LOGITS
     n
    0.52
     Vertical
    0.52
     verticale
    0.51
     vertical
    0.49
     Libert
    0.49
     niemand
    0.49
     المال
    0.48
     veget
    0.48
    eft
    0.48
     sonst
    0.47
    Activations Density 0.001%

    No Known Activations