© 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. 124480
    Prev
    Next
    INDEX
    Explanations

    phrasal structure following common tokens

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

    institutional investor, reverse proxy, mercenary motivation

    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
    to
    0.65
    k
    0.64
    f
    0.62
    lar
    0.62
    il
    0.59
    Extra
    0.57
    ad
    0.53
    o
    0.53
    ter
    0.53
    om
    0.51
    POSITIVE LOGITS
    ⦖
    0.57
     fermé
    0.49
    ເຂ
    0.48
     cerrado
    0.48
     mogę
    0.48
     pdelay
    0.47
    ꯦ
    0.46
     вя
    0.44
    વાહી
    0.43
     gonflement
    0.43
    Activations Density 0.000%

    No Known Activations