© 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. 38109
    Prev
    Next
    INDEX
    Explanations

    matte nails, asylum seeker, World Environment Day

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

    mystery noir, servant whom

    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
     шан
    0.49
     Гер
    0.46
    UCK
    0.46
    чком
    0.46
    Z
    0.45
    翦
    0.45
    SuccessListener
    0.44
     अच
    0.43
    වු
    0.43
    ल
    0.43
    POSITIVE LOGITS
     beforePath
    0.47
    ilot
    0.44
    adays
    0.43
    threads
    0.43
     decentral
    0.43
     Advocates
    0.42
    kap
    0.42
    hiyam
    0.42
    até
    0.42
    irez
    0.41
    Activations Density 0.000%

    No Known Activations