© 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. 5640
    Prev
    Next
    INDEX
    Explanations

    markers and sequences

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

    Norwegian, Mushrooms, moving

    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
    पूर्ति
    0.42
     свидетель
    0.41
    𝖚
    0.41
     серд
    0.41
     سنه
    0.41
    MovieDetails
    0.40
     certificado
    0.40
    珹
    0.40
     crimin
    0.39
    UPLOAD
    0.39
    POSITIVE LOGITS
     QA
    0.45
     Mac
    0.44
     Lors
    0.42
     l
    0.42
    Lr
    0.42
     CB
    0.42
     ব্যার্থ
    0.41
     ,
    0.41
     only
    0.41
     )
    0.41
    Activations Density 0.001%

    No Known Activations