© 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. 13614
    Prev
    Next
    INDEX
    Explanations

    components or actions followed by specific continuations

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

    specific protocol. WHERE clause. configuration

    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
    е
    0.35
    р
    0.35
    ิ
    0.35
    ล
    0.34
    ะ
    0.34
    ด
    0.34
     величе
    0.32
    า
    0.32
    ี
    0.32
    מ
    0.31
    POSITIVE LOGITS
     participating
    0.28
     comprises
    0.27
     xyz
    0.26
     during
    0.26
     simonsen
    0.25
     patties
    0.25
     dimer
    0.25
    )。
    0.25
     chromatographed
    0.25
     stationed
    0.24
    Activations Density 0.054%

    No Known Activations