© 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. 67730
    Prev
    Next
    INDEX
    Explanations

    live music

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

    Link in bio tool

    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
    沃
    0.51
    inizin
    0.49
    طه
    0.49
    기를
    0.48
    最小值
    0.47
    髋
    0.47
     anmelden
    0.46
    헹
    0.45
    Initialization
    0.45
    遇见
    0.44
    POSITIVE LOGITS
     điển
    0.47
    দিগের
    0.46
     puerta
    0.45
     дверей
    0.44
     الاشت
    0.43
     puertas
    0.42
     cái
    0.42
     चंद
    0.42
    ದೆ
    0.42
     organise
    0.41
    Activations Density 0.000%

    No Known Activations