© 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. 132865
    Prev
    Next
    INDEX
    Explanations

    foreign language book titles

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

    fulfilling requested styles and context

    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
    在新
    0.44
    降
    0.44
    assin
    0.43
    ὴ
    0.43
    ASS
    0.42
    `<
    0.42
    oring
    0.42
    )}$,
    0.42
    不管
    0.42
    めに
    0.41
    POSITIVE LOGITS
     penulis
    0.59
    仨
    0.55
    ന്ത
    0.52
     lettura
    0.52
     ospiti
    0.52
     sabores
    0.51
     escritores
    0.50
     cucina
    0.50
     স্থিত
    0.49
     penjelasan
    0.49
    Activations Density 0.001%

    No Known Activations