© 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. 168874
    Prev
    Next
    INDEX
    Explanations

    opportunities

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

    blueprint representation

    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
     Schm
    0.47
     الفلسط
    0.46
    lnk
    0.43
     فلسط
    0.42
     زع
    0.42
    NAME
    0.42
     Schu
    0.42
     ទ
    0.42
     シェ
    0.42
    us
    0.42
    POSITIVE LOGITS
     compresses
    0.48
     deliciously
    0.47
    빗
    0.47
     relieves
    0.46
     dainty
    0.46
    ινε
    0.45
     densidad
    0.45
     spectacularly
    0.44
    ভূতি
    0.44
    макра
    0.44
    Activations Density 0.001%

    No Known Activations