© 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. 31-GEMMASCOPE-2-RES-262K
    7. 41807
    Prev
    Next
    INDEX
    Explanations

    comparing understanding depths

    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_31_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
     utilizan
    0.45
    ത്തിലാണ്
    0.45
    🐀
    0.45
    usp
    0.44
     ########.
    0.42
     distingue
    0.41
     найбільш
    0.41
     rin
    0.41
     désigne
    0.41
    nicu
    0.41
    POSITIVE LOGITS
    وي
    0.47
    溘
    0.43
    时候
    0.43
    全身
    0.42
    或者
    0.42
     सुद्धा
    0.42
    вати
    0.42
    érer
    0.41
    ம்ப
    0.41
    发射
    0.40
    Activations Density 0.010%

    No Known Activations