© 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. 151467
    Prev
    Next
    INDEX
    Explanations

    interview leads to question

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

    identifying targets and queues

    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
    an
    0.57
    ان
    0.53
    െല്ലാം
    0.49
    手
    0.46
     battle
    0.46
     remained
    0.46
     utilisateurs
    0.45
     조
    0.45
    אנ
    0.45
    to
    0.44
    POSITIVE LOGITS
     Contempor
    0.50
    𝐯
    0.50
     Hogg
    0.46
     Flying
    0.46
     Rear
    0.44
     băng
    0.44
     workman
    0.44
     पिक्च
    0.43
     गिवन
    0.43
    വു
    0.43
    Activations Density 0.001%

    No Known Activations