© 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. 52562
    Prev
    Next
    INDEX
    Explanations

    not both

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

    how to protect

    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
     अर
    0.46
    ರ್
    0.46
    ectable
    0.45
    ehr
    0.44
    IT
    0.42
    9
    0.42
     মনের
    0.42
     pfl
    0.41
    ER
    0.41
    8
    0.41
    POSITIVE LOGITS
     لازم
    0.51
    ßerdem
    0.48
    lle
    0.45
     Ländern
    0.45
     Kurs
    0.44
     خبر
    0.43
     மேற்கொள்ள
    0.43
    ildir
    0.43
    פן
    0.43
    нняя
    0.43
    Activations Density 0.000%

    No Known Activations