© 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. 128006
    Prev
    Next
    INDEX
    Explanations

    Adding

    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
    ר
    0.51
     संयंत्र
    0.47
    important
    0.47
    ه
    0.47
    瑁
    0.47
     Newmarket
    0.46
    เธอ
    0.46
     khuẩn
    0.45
     privaten
    0.45
    atrième
    0.44
    POSITIVE LOGITS
     initializes
    0.46
    ieves
    0.42
     Everybody
    0.42
    up
    0.41
    esa
    0.41
    :
    0.41
    istles
    0.40
     Cependant
    0.40
    cible
    0.40
    っと
    0.39
    Activations Density 0.004%

    No Known Activations