© 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. 8620
    Prev
    Next
    INDEX
    Explanations

    available in, the easiest, any submarine

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

    can or what questions

    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
     allgeme
    0.61
    FURNIZOR
    0.60
    ل
    0.59
     on
    0.57
    ありが
    0.55
    كبر
    0.55
     feit
    0.54
     üçüncü
    0.54
     has
    0.54
     engulfed
    0.53
    POSITIVE LOGITS
    ।
    0.84
    。
    0.80
    UR
    0.71
    _
    0.71
    EN
    0.68
    RA
    0.68
    ។
    0.66
    ORE
    0.66
    you
    0.63
    0.62
    Activations Density 0.321%

    No Known Activations