© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 21473
    Prev
    Next
    INDEX
    Explanations

    increases prices

    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
    <0xCB>
    0.43
     cardNumber
    0.43
     Sold
    0.43
    Sold
    0.43
     Sự
    0.41
     assignee
    0.41
    Ֆ
    0.41
    ンプル
    0.41
    DIE
    0.41
     pineapple
    0.40
    POSITIVE LOGITS
     வடி
    0.43
     terapi
    0.43
     теорети
    0.41
     اتفاق
    0.41
     участников
    0.41
     teore
    0.40
    剐
    0.40
    硌
    0.40
     equilibrated
    0.39
    饬
    0.39
    Activations Density 0.004%

    No Known Activations