© 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. 3463
    Prev
    Next
    INDEX
    Explanations

    a 's

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

    forms of

    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
     ид
    0.38
    咿
    0.37
     માતા
    0.36
     માટે
    0.36
    getId
    0.36
     அழக
    0.35
     यानी
    0.35
    🧒
    0.35
    ';
    0.34
     помога
    0.34
    POSITIVE LOGITS
     unmittelbar
    0.39
     przedsi
    0.37
     assorted
    0.35
     अपेक्षाकृत
    0.35
     সম্ভবত
    0.34
     discretionary
    0.34
     निर्धारण
    0.34
     hasten
    0.33
     hipot
    0.32
     serviceable
    0.32
    Activations Density 0.012%

    No Known Activations