© 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. 100682
    Prev
    Next
    INDEX
    Explanations

    field, cars, relevant, essay, fault, not

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

    rapid advancements

    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
    炵
    0.48
    rafi
    0.48
    rafos
    0.47
    iffent
    0.47
    haram
    0.46
     transforming
    0.45
     socialism
    0.45
     escolher
    0.44
    اية
    0.44
    ायतों
    0.44
    POSITIVE LOGITS
     က
    0.50
    က
    0.49
    GROUP
    0.47
    ª
    0.46
    Describe
    0.45
    ne
    0.44
    Grupo
    0.44
    TEAM
    0.43
     Adv
    0.43
    EN
    0.42
    Activations Density 0.000%

    No Known Activations