© 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. 78507
    Prev
    Next
    INDEX
    Explanations

    He gave to forget

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

    dogs and lists

    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
    am
    0.48
    ректор
    0.48
    uduk
    0.46
     въз
    0.45
    сім
    0.43
    ikul
    0.43
    ]_
    0.43
     trilogy
    0.42
     Trio
    0.42
    bih
    0.41
    POSITIVE LOGITS
     CREATE
    0.53
    CREATE
    0.51
    د
    0.49
    ORDAN
    0.48
    洴
    0.46
     llenar
    0.45
     বলেছি
    0.45
     timeouts
    0.45
    ك
    0.45
     PROCED
    0.45
    Activations Density 0.000%

    No Known Activations