© 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. 245332
    Prev
    Next
    INDEX
    Explanations

    common words followed by specific words

    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
    ائن
    0.56
    یکه
    0.45
    بوع
    0.44
    Subject
    0.43
    قاف
    0.42
    سم
    0.42
    ließ
    0.41
    擰
    0.41
    اداسی
    0.41
    لاة
    0.40
    POSITIVE LOGITS
    ul
    0.57
    ą
    0.52
    NI
    0.52
     beautiful
    0.49
    yl
    0.49
     equations
    0.49
     lotion
    0.49
    EEE
    0.48
     choices
    0.48
     questions
    0.47
    Activations Density 0.001%

    No Known Activations