© 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. 114897
    Prev
    Next
    INDEX
    Explanations

    Box PC

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

    a noun or context

    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
     bosons
    0.49
     ي
    0.48
     garlands
    0.47
     activid
    0.46
     reales
    0.46
     amigos
    0.46
     valeurs
    0.45
     empleados
    0.45
     enjoined
    0.44
    می
    0.44
    POSITIVE LOGITS
    g
    0.53
    ők
    0.49
    ul
    0.46
    ist
    0.43
    it
    0.43
    ator
    0.43
    িস্ট
    0.42
    ąć
    0.42
     திரை
    0.41
    ítható
    0.41
    Activations Density 0.000%

    No Known Activations