© 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. 133205
    Prev
    Next
    INDEX
    Explanations

    collected anonymously, excellent service, follow official

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

    filming, utterance, balance, maintain

    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
     virgin
    0.49
     света
    0.46
    ．
    0.46
     militar
    0.46
     piggy
    0.45
    quartz
    0.44
     mulberry
    0.43
     servici
    0.43
    venus
    0.43
    穎
    0.42
    POSITIVE LOGITS
     এড়িয়ে
    0.49
     expressive
    0.47
     Invasive
    0.47
    aras
    0.45
     αποφ
    0.41
     참여
    0.41
    其中包括
    0.39
    晴
    0.39
     Breath
    0.39
     Futures
    0.39
    Activations Density 0.001%

    No Known Activations