© 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. 42259
    Prev
    Next
    INDEX
    Explanations

    foreign/special characters and punctuation

    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
    戙
    0.46
    Arguments
    0.42
     Shout
    0.42
     Away
    0.42
     depolarization
    0.41
    Amazing
    0.40
    拁
    0.40
    Alright
    0.40
    㴓
    0.40
    紶
    0.39
    POSITIVE LOGITS
    uthers
    0.46
    anches
    0.46
    askar
    0.44
    ethnic
    0.43
     descarga
    0.43
     encircled
    0.42
     옳
    0.42
    usias
    0.41
     teis
    0.41
    ǎ
    0.41
    Activations Density 0.004%

    No Known Activations