© 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. 161234
    Prev
    Next
    INDEX
    Explanations

    installation, substitutes, issue

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

    Anakin Skywalker

    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
     упо
    0.49
     فِي
    0.48
    বে
    0.47
     desenvolved
    0.45
    끽
    0.44
     бе
    0.44
     Heap
    0.43
    মোহ
    0.43
    辣
    0.42
     આવી
    0.42
    POSITIVE LOGITS
    voirs
    0.49
    ینہ
    0.46
    可以看出
    0.46
     irreparable
    0.46
     solidification
    0.44
     arteries
    0.44
     liners
    0.43
     adolescence
    0.43
    并将
    0.43
    레스
    0.43
    Activations Density 0.001%

    No Known Activations