© 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. 54687
    Prev
    Next
    INDEX
    Explanations

    formal or complex words

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

    complex relationships and concepts

    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
    ad
    1.37
    n
    1.33
    et
    1.29
    ia
    1.17
    il
    1.15
     I
    1.15
    id
    1.13
    v
    1.13
     It
    1.11
    ag
    1.10
    POSITIVE LOGITS
    も
    1.09
    ও
    1.01
     σε
    0.98
     vestiges
    0.89
    在
    0.85
     في
    0.82
     лише
    0.81
     médicas
    0.80
     furiously
    0.80
    კ
    0.79
    Activations Density 0.285%

    No Known Activations