© 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. 245560
    Prev
    Next
    INDEX
    Explanations

    place names February transaction

    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
     NRI
    0.53
    NRI
    0.49
     Cornerstone
    0.47
    伀
    0.46
    แท
    0.45
     CIS
    0.44
     буквально
    0.44
     Merry
    0.43
    ર
    0.42
    clude
    0.42
    POSITIVE LOGITS
    않
    0.56
     clínica
    0.48
     prothorace
    0.47
     attendre
    0.47
    귓
    0.46
     estrés
    0.45
     anesthesia
    0.45
    calf
    0.45
     estabilidad
    0.44
     দৈর্ঘ
    0.44
    Activations Density 0.001%

    No Known Activations