© 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. 47357
    Prev
    Next
    INDEX
    Explanations

    Isaiah and prophecy

    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
     Salazar
    0.43
     Malay
    0.42
     सल
    0.42
     tespit
    0.41
     composée
    0.40
     quan
    0.39
     Frankly
    0.39
    宓
    0.39
     Malayalam
    0.39
     facing
    0.38
    POSITIVE LOGITS
    Coal
    0.47
    Isaiah
    0.46
    newTask
    0.45
     Isaiah
    0.43
    Illinois
    0.42
    Chicago
    0.40
    stanza
    0.40
    脛
    0.38
    ベル
    0.38
    create
    0.37
    Activations Density 0.005%

    No Known Activations