© 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. 154901
    Prev
    Next
    INDEX
    Explanations

    when discussing when, when not

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

    golang code

    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
    ﮧ
    0.49
    Ｍ
    0.48
    いた
    0.48
    數
    0.45
    ओम
    0.43
    衛
    0.43
    ках
    0.42
    Ｂ
    0.42
    H
    0.42
    пер
    0.41
    POSITIVE LOGITS
     cuándo
    0.52
     όταν
    0.49
     When
    0.46
     LPTMR
    0.46
     Projects
    0.45
     candidatura
    0.44
     Když
    0.44
     عندما
    0.44
     proposte
    0.44
     cuando
    0.44
    Activations Density 0.001%

    No Known Activations