© 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. 177235
    Prev
    Next
    INDEX
    Explanations

    dedicated server

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

    explosion *in* space

    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
    tema
    0.48
    。「
    0.47
    ᱾
    0.46
    ringa
    0.45
    Kuota
    0.45
    targeted
    0.45
    rivia
    0.45
    。《
    0.44
    terre
    0.42
    tet
    0.42
    POSITIVE LOGITS
    وڈ
    0.47
    oram
    0.45
    书
    0.45
    其他
    0.44
     keySchedule
    0.43
    우
    0.43
    클
    0.42
    ن
    0.42
    원
    0.42
     kdy
    0.42
    Activations Density 0.000%

    No Known Activations