© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 90503
    Prev
    Next
    INDEX
    Explanations

    specific scenarios or actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    мо
    0.57
    ת
    0.54
    敺
    0.52
    ອອກ
    0.51
     triển
    0.50
     ইয়াহিয়ার
    0.50
    чни
    0.50
    прода
    0.50
    מן
    0.50
    тики
    0.50
    POSITIVE LOGITS
     <
    0.47
    .".
    0.45
     as
    0.45
     designates
    0.43
     혹은
    0.41
     bun
    0.40
     (.
    0.40
     (<
    0.40
    ).
    0.40
     circa
    0.40
    Activations Density 0.001%

    No Known Activations