© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 143389
    Prev
    Next
    INDEX
    Explanations

    inherent qualities or transformations

    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
    тите
    0.45
    творе
    0.42
    щений
    0.42
    time
    0.41
     modifier
    0.40
    ф
    0.40
    try
    0.38
    OTA
    0.38
    те
    0.38
    screen
    0.38
    POSITIVE LOGITS
     intégral
    0.51
    aceae
    0.49
     melting
    0.48
     originality
    0.46
     equilateral
    0.46
    ཌ
    0.45
     melanin
    0.45
     uniqueness
    0.44
     melts
    0.44
     डिप्लोमा
    0.44
    Activations Density 0.007%

    No Known Activations