© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 52952
    Prev
    Next
    INDEX
    Explanations

    sown perennial crops

    np_acts-logits-general · gemini-2.5-flash-lite

    western greetings and cowboy emoji

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    s
    0.55
    س
    0.50
    тт
    0.47
    с
    0.47
     procl
    0.46
    ла
    0.46
     kampany
    0.45
    ف
    0.43
    Сегодня
    0.43
    риал
    0.43
    POSITIVE LOGITS
     ఉన్న
    0.44
    Longrightarrow
    0.44
     étudiants
    0.44
     oligonucleotide
    0.43
    FunctionName
    0.43
     motionProxy
    0.43
     sphing
    0.43
     immunoprec
    0.42
     displayNumber
    0.42
     rencontr
    0.42
    Activations Density 0.000%

    No Known Activations