© 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. 64330
    Prev
    Next
    INDEX
    Explanations

    relationship of

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

    levels and categories

    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
     Yankees
    0.48
    u
    0.46
     quien
    0.45
     सादर
    0.43
     cu
    0.43
     cuyo
    0.41
     ή
    0.41
     PDPN
    0.41
     Rodr
    0.40
     Embora
    0.40
    POSITIVE LOGITS
    Daten
    0.49
     보안
    0.47
     земель
    0.47
    ረው
    0.46
     상세
    0.45
    Datas
    0.45
    енты
    0.44
    Theoretical
    0.44
     artefacts
    0.44
    밤
    0.44
    Activations Density 0.000%

    No Known Activations