© 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. 160612
    Prev
    Next
    INDEX
    Explanations

    instructions or descriptions

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

    lists of numbers 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-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
     успе
    0.49
     STATIC
    0.49
    Visitation
    0.48
    resting
    0.46
    牍
    0.46
    軎
    0.45
    Applicants
    0.45
    静态
    0.45
    urbation
    0.45
    ﺌ
    0.45
    POSITIVE LOGITS
     rumin
    0.46
     conco
    0.43
     stretch
    0.43
     recoil
    0.43
     rudder
    0.43
     stretches
    0.42
     regul
    0.41
     tubular
    0.41
     helical
    0.41
     gun
    0.40
    Activations Density 0.001%

    No Known Activations