© 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. 139343
    Prev
    Next
    INDEX
    Explanations

    sequences of words following common words

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

    Unable to execute commands

    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
    ة
    0.55
    ਮ
    0.54
    वे
    0.52
    ী
    0.51
    า
    0.50
    ве
    0.50
    ing
    0.49
    قر
    0.46
    ת
    0.46
    upy
    0.46
    POSITIVE LOGITS
    silyl
    0.46
     इंग्ल
    0.45
     సమయంలో
    0.45
     GameManager
    0.45
     yù
    0.44
    ljeni
    0.44
     deterred
    0.44
    *"
    0.44
    <unused95>
    0.43
     *"
    0.43
    Activations Density 0.001%

    No Known Activations