© 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. 53-GEMMASCOPE-2-RES-262K
    7. 12188
    Prev
    Next
    INDEX
    Explanations

    3D concepts

    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_53_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
    ровкой
    0.41
     পারছি
    0.41
    靕
    0.40
    ствуйте
    0.40
    ње
    0.39
    grandchildren
    0.39
    isBlank
    0.39
    𝖐
    0.39
    фици
    0.38
    ğraf
    0.38
    POSITIVE LOGITS
    d
    1.90
    ｄ
    1.54
    ds
    1.52
    д
    1.51
    د
    1.45
    ד
    1.41
    ْد
    1.36
    <0x93>
    1.34
    ԁ
    1.34
    𝖽
    1.34
    Activations Density 0.055%

    No Known Activations