© 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. 190714
    Prev
    Next
    INDEX
    Explanations

    dissertations and futuredespite dosegrants forread current

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

    specifying alternatives or conditions

    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
    אַ
    0.56
    <0xE7>
    0.52
     אַ
    0.50
    ק
    0.49
    კო
    0.47
    ਾ
    0.47
    לי
    0.46
    מ
    0.46
    т
    0.45
    סק
    0.45
    POSITIVE LOGITS
     ataupun
    0.78
     কিংবা
    0.75
     their
    0.72
     these
    0.70
     hoặc
    0.67
     &/
    0.66
     অথবা
    0.64
     leurs
    0.64
     eller
    0.63
     maupun
    0.63
    Activations Density 0.000%

    No Known Activations