© 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. 127467
    Prev
    Next
    INDEX
    Explanations

    vulnerability, planet, hashtags, transactions

    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
    =".
    0.48
     humankind
    0.48
     multitudes
    0.47
     |,
    0.46
    sı
    0.45
    II
    0.45
     complica
    0.45
    ers
    0.45
    Į
    0.44
     |.
    0.44
    POSITIVE LOGITS
     و
    0.53
     marketing
    0.50
    را
    0.47
     Shadows
    0.46
     ز
    0.45
     krok
    0.44
    az
    0.44
     पवित्र
    0.43
    дым
    0.41
     وق
    0.41
    Activations Density 0.000%

    No Known Activations