© 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. 2530
    Prev
    Next
    INDEX
    Explanations

    indicating a start or range

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

    from X to Y

    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
    有两种
    0.38
     অথবা
    0.36
     oppure
    0.36
     hoặc
    0.35
     or
    0.35
    或者
    0.35
     ],
    0.34
     Zusammenhang
    0.34
     },
    0.33
     beiden
    0.33
    POSITIVE LOGITS
     እስከ
    0.57
    desde
    0.52
     લઈને
    0.52
     अगदी
    0.49
     έως
    0.49
    부터
    0.49
     inception
    0.48
     लेकर
    0.47
     শুরু
    0.47
     piccoli
    0.46
    Activations Density 0.126%

    No Known Activations