© 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. 218355
    Prev
    Next
    INDEX
    Explanations

    unique collection pieces

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

    request, gap, or releases

    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
     Христос
    0.51
    Ⲛ
    0.50
     ఇందులో
    0.48
     н
    0.48
     воде
    0.47
    وزيع
    0.46
     paradig
    0.46
     Nachrichten
    0.46
     Теле
    0.46
     Dienste
    0.45
    POSITIVE LOGITS
    nodemon
    0.51
    develop
    0.48
     développ
    0.44
    oció
    0.43
    occhi
    0.42
    国外
    0.42
    ताई
    0.42
    没
    0.41
    یش
    0.41
     cod
    0.41
    Activations Density 0.000%

    No Known Activations