© 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. 10151
    Prev
    Next
    INDEX
    Explanations

    architect, compress, solutions

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

    support or with

    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
    Ꮭ
    0.23
     doit
    0.21
     escolares
    0.20
    Ꮔ
    0.20
    واں
    0.20
     derniers
    0.20
    ман
    0.19
    вых
    0.19
    ዖ
    0.19
     transacción
    0.19
    POSITIVE LOGITS
    rez
    0.22
    ujem
    0.22
    ielle
    0.21
    eping
    0.21
    örg
    0.21
     رفض
    0.21
     විශ
    0.20
    rom
    0.20
     Alonso
    0.20
    okok
    0.20
    Activations Density 0.003%

    No Known Activations