© 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. 182805
    Prev
    Next
    INDEX
    Explanations

    Sal

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

    SMILES notation subunits

    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
    .
    0.47
    ;
    0.46
    ↵
    0.44
     ;
    0.44
     ^{
    0.43
     an
    0.41
     Airways
    0.40
     the
    0.39
    .;
    0.39
    DAO
    0.39
    POSITIVE LOGITS
    kennung
    0.48
    𒁉
    0.46
    釹
    0.45
    <unused0>
    0.45
    מן
    0.44
    нением
    0.44
    ้ม
    0.43
     গুগল
    0.43
    甛
    0.43
    ⊱
    0.42
    Activations Density 0.001%

    No Known Activations