© 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. 53694
    Prev
    Next
    INDEX
    Explanations

    information files and snowboarding

    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
    痺
    0.51
     pianta
    0.44
     مسئلے
    0.44
     resorption
    0.43
    drying
    0.43
     spacetime
    0.42
     poverty
    0.42
     summing
    0.42
    <th>
    0.41
    odeficiency
    0.41
    POSITIVE LOGITS
     veröffent
    0.48
    b
    0.45
    nemen
    0.43
     vás
    0.41
     promot
    0.40
     Bri
    0.40
    ennzeichnet
    0.40
    밧
    0.40
     정말
    0.40
     Zet
    0.40
    Activations Density 0.006%

    No Known Activations