© 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. 156308
    Prev
    Next
    INDEX
    Explanations

    example from DirectTV

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

    mitigated, enabled, funny

    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
    萜
    0.43
    ATHER
    0.40
    ETING
    0.40
     ίδ
    0.40
    起こ
    0.39
     topik
    0.38
     refracting
    0.38
    INES
    0.38
     чемпиона
    0.38
     কয়েকটি
    0.38
    POSITIVE LOGITS
    जारत
    0.43
    notify
    0.41
    जेश
    0.41
     hassles
    0.40
     kayıt
    0.40
    <unused506>
    0.40
    Ყ
    0.40
    च्छ
    0.39
    维护
    0.39
    FormControl
    0.39
    Activations Density 0.000%

    No Known Activations