© 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. 98270
    Prev
    Next
    INDEX
    Explanations

    bids or tackled topics

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

    barrier with, Earth relatively, Think step

    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
    DAY
    0.44
    IDX
    0.44
    DD
    0.43
    DIY
    0.43
    ಫ
    0.43
    차
    0.42
    ’
    0.41
     categories
    0.41
    inton
    0.41
    發
    0.41
    POSITIVE LOGITS
    ఎల్
    0.49
     pprint
    0.46
     ơn
    0.46
     vanwege
    0.46
     Vergangenheit
    0.45
     definir
    0.45
     المرسلين
    0.44
     analizar
    0.43
     discutir
    0.43
     ശങ്ക
    0.42
    Activations Density 0.002%

    No Known Activations