© 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. 33920
    Prev
    Next
    INDEX
    Explanations

    essay pdf

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

    thesis, advanced analytics, clustering

    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
     ಲಿ
    0.50
    𝗼
    0.49
    𝗺
    0.49
     cambiando
    0.48
    𝐞
    0.48
    irli
    0.47
     redefining
    0.47
    rvats
    0.46
    𝘂
    0.46
    ነት
    0.45
    POSITIVE LOGITS
     thesis
    0.45
    ৎ
    0.43
    凹
    0.42
    上面
    0.41
    平时
    0.41
    maintained
    0.41
    ধে
    0.39
    凸
    0.39
    饥
    0.39
    单纯
    0.39
    Activations Density 0.000%

    No Known Activations