© 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. 89954
    Prev
    Next
    INDEX
    Explanations

    recipe information

    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
     spring
    0.45
    ع
    0.43
    尖
    0.42
    3
    0.41
    9
    0.41
    장을
    0.40
    Pedro
    0.40
    ائب
    0.40
    隽
    0.39
    يد
    0.39
    POSITIVE LOGITS
     atleta
    0.59
    नाथन
    0.57
     किताब
    0.52
     इम्यून
    0.51
    fficient
    0.49
    )”
    0.49
     obliv
    0.47
    ).”
    0.47
     मिथ
    0.46
     マット
    0.46
    Activations Density 0.001%

    No Known Activations