© 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-65K
    7. 35724
    Prev
    Next
    INDEX
    Explanations

    Euclid, perpetrators, winning, increment

    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_65k_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
    سر
    0.54
    zące
    0.49
    埓
    0.49
     साम
    0.45
    ล่าสุด
    0.45
    וב
    0.45
    sendStatus
    0.45
    سین
    0.43
     myśl
    0.43
    ָ
    0.42
    POSITIVE LOGITS
     Politik
    0.47
     attest
    0.43
    deload
    0.42
    ផ្ស
    0.42
     publications
    0.42
    alahan
    0.42
     constituyen
    0.42
     rentable
    0.42
    apikey
    0.41
     consommateurs
    0.41
    Activations Density 0.002%

    No Known Activations