© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 4918
    Prev
    Next
    INDEX
    Explanations

    visual introductions

    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
    ০০
    0.42
     қу
    0.41
    द्र
    0.39
     จึง
    0.37
    欤
    0.37
    Race
    0.36
    :")
    0.36
    ượt
    0.36
     ควร
    0.35
    槛
    0.35
    POSITIVE LOGITS
     debut
    0.42
     Anthony
    0.42
     hard
    0.42
    synthetic
    0.41
     synthetic
    0.40
    debut
    0.40
     oxidative
    0.40
     str
    0.38
     LA
    0.38
     ruthenium
    0.37
    Activations Density 0.001%

    No Known Activations