© 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. 50514
    Prev
    Next
    INDEX
    Explanations

    starts with specific words

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

    Option 1 (Concise & Clear)

    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
     moths
    0.51
     firstly
    0.49
    ँची
    0.49
    چھا
    0.46
    ０
    0.46
     emailing
    0.45
    lsulfanyl
    0.44
     શહેર
    0.44
    ٹھ
    0.43
    ಬೇವಿನ
    0.43
    POSITIVE LOGITS
    <blockquote>
    0.58
    passage
    0.52
     passage
    0.47
     Passage
    0.47
     म्हट
    0.46
    p
    0.44
    <0x0D>
    0.41
    implies
    0.41
     extravag
    0.40
     passages
    0.40
    Activations Density 0.004%

    No Known Activations