© 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. 128771
    Prev
    Next
    INDEX
    Explanations

    As followed by clause or phrase

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

    as followed by a word

    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
     Sabemos
    0.55
    Nic
    0.50
    Somos
    0.50
     sabemos
    0.50
    Kita
    0.50
    뵌
    0.49
    никова
    0.46
    Estamos
    0.45
    يون
    0.44
    Shown
    0.43
    POSITIVE LOGITS
     தொடங்கியது
    0.44
     consort
    0.44
     forbade
    0.43
     inauguration
    0.43
     guarantor
    0.43
     presumptive
    0.43
    ☛
    0.42
     unusually
    0.42
    êng
    0.42
    っていました
    0.41
    Activations Density 0.038%

    No Known Activations