© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 3489
    Prev
    Next
    INDEX
    Explanations

    code definitions and mathematical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ера
    0.49
    р
    0.46
    ERE
    0.46
    :
    0.45
    ASE
    0.43
     promulgating
    0.43
     separator
    0.41
    נס
    0.41
     scarlet
    0.41
    м
    0.41
    POSITIVE LOGITS
     оттен
    0.54
    ᄈ
    0.52
     कक्क
    0.48
    ozen
    0.48
     তখনকার
    0.47
     मैथमेट
    0.47
     Entered
    0.47
     ಬೇಕ
    0.46
    Ѡ
    0.46
    angulo
    0.46
    Activations Density 0.000%

    No Known Activations