© 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. 5601
    Prev
    Next
    INDEX
    Explanations

    particularly on/for

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

    especially if or for

    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
     tuttavia
    0.21
     Однако
    0.20
     bzw
    0.19
     tačiau
    0.19
     αλλά
    0.19
     تاہم
    0.18
     Ꭰ
    0.18
     ),
    0.18
     thiab
    0.18
     Entretanto
    0.17
    POSITIVE LOGITS
     with
    0.31
     עם
    0.29
     dengan
    0.28
     from
    0.26
     in
    0.25
    dengan
    0.24
     với
    0.24
     for
    0.23
     on
    0.23
    ใน
    0.21
    Activations Density 0.799%

    No Known Activations