© 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-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 44181
    Prev
    Next
    INDEX
    Explanations

    EPS file format

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    。
    0.98
    d
    0.96
    i
    0.90
    dengan
    0.82
    )،
    0.80
    К
    0.79
    Ре
    0.79
    ۔
    0.79
    Б
    0.77
    k
    0.76
    POSITIVE LOGITS
    ната
    0.74
    ate
    0.71
     to
    0.70
    ну
    0.67
    ва
    0.66
    на
    0.64
    ospital
    0.64
    ,
    0.64
    iber
    0.62
    ando
    0.61
    Activations Density 0.000%

    No Known Activations