© 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. 223845
    Prev
    Next
    INDEX
    Explanations

    UNESCO World Heritage Site

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

    noun noun pairs

    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
     conditional
    0.50
     tev
    0.47
     italics
    0.46
    .//
    0.46
    .³
    0.44
     apical
    0.44
    Conditional
    0.44
     ./
    0.43
     italic
    0.42
     Conditional
    0.42
    POSITIVE LOGITS
    ódio
    0.47
    urados
    0.47
     olmayan
    0.46
    řed
    0.45
    pessoas
    0.45
    घर
    0.45
    किस्तानी
    0.45
    ట్స్‌మన్
    0.44
    क्ताओं
    0.44
    ниците
    0.44
    Activations Density 0.257%

    No Known Activations