© 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. 10308
    Prev
    Next
    INDEX
    Explanations

    comment markers and code syntax

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

    instructional keywords

    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
    <unused2121>
    0.24
    林
    0.22
    .;
    0.22
         
    0.21
    <unused2117>
    0.21
     أيضًا
    0.21
    曾
    0.21
    ().
    0.20
    cion
    0.20
    Universität
    0.20
    POSITIVE LOGITS
     get
    0.39
     first
    0.36
     try
    0.34
     पहले
    0.32
     check
    0.31
     find
    0.30
     getting
    0.30
     inset
    0.30
     add
    0.29
     Typical
    0.29
    Activations Density 0.001%

    No Known Activations