© 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. 217110
    Prev
    Next
    INDEX
    Explanations

    common initiators of phrases

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

    planned obsolescence, modular design

    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
     unrivalled
    0.46
     Бе
    0.46
     쪽
    0.45
    ں
    0.45
     be
    0.45
     arrears
    0.44
    ^-
    0.44
     caries
    0.43
     ایش
    0.42
     failings
    0.42
    POSITIVE LOGITS
    તાઓ
    0.56
    海水
    0.52
    IZER
    0.52
    MENT
    0.51
    PUT
    0.51
    IO
    0.50
    化
    0.50
    CREATE
    0.49
    INTE
    0.48
     agreg
    0.48
    Activations Density 0.001%

    No Known Activations