© 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. 16628
    Prev
    Next
    INDEX
    Explanations

    negation, absence, or statements of fact

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

    nothingness in multiple languages

    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
     kaise
    0.41
     rozp
    0.38
     જન્મ
    0.38
     génération
    0.37
     déta
    0.36
     confertim
    0.36
     thèse
    0.36
    厸
    0.36
    㱛
    0.36
     बिंद
    0.36
    POSITIVE LOGITS
     ninguna
    1.23
    NONE
    1.15
     none
    1.13
     nenhum
    1.13
     keine
    1.10
     nenhuma
    1.09
    None
    1.09
    没有任何
    1.08
    ไม่มี
    1.07
     None
    1.06
    Activations Density 0.039%

    No Known Activations