© 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. 35324
    Prev
    Next
    INDEX
    Explanations

    follows specific words

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

    limited order buying

    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
    imètre
    0.50
    НІ
    0.48
    inicio
    0.48
    onnées
    0.47
    ੦
    0.47
    cèle
    0.47
    نیٹ
    0.47
    média
    0.46
    entrada
    0.46
    larghezza
    0.46
    POSITIVE LOGITS
    ب
    0.51
     equiv
    0.50
     due
    0.49
     Technician
    0.49
     accom
    0.48
     assertTrue
    0.48
     chevron
    0.46
     Upan
    0.45
    ли
    0.44
     appContext
    0.44
    Activations Density 0.000%

    No Known Activations