© 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. 39179
    Prev
    Next
    INDEX
    Explanations

    is not another

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

    authentic people adjacent

    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
     RSVP
    0.49
     Granny
    0.48
    /
    0.48
     Ryanair
    0.48
    Terry
    0.47
    提起
    0.47
     RSA
    0.46
    際の
    0.46
     препо
    0.45
     Kickstarter
    0.45
    POSITIVE LOGITS
     مشرقی
    0.48
    kirche
    0.47
     enriched
    0.46
    adap
    0.46
    ون
    0.45
     آم
    0.45
     gde
    0.45
    洴
    0.44
    แมนเชสเตอร์ซิตี
    0.44
     Mascul
    0.44
    Activations Density 0.000%

    No Known Activations