© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 19544
    Prev
    Next
    INDEX
    Explanations

    technical or societal entities

    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
     आणि
    0.59
    และ
    0.59
     এবং
    0.54
     以及
    0.52
     અને
    0.51
     그리고
    0.51
     और
    0.51
     и
    0.50
     ۽
    0.50
    并在
    0.50
    POSITIVE LOGITS
    ↵↵
    0.43
     days
    0.41
    ;
    0.40
    ↵↵↵
    0.39
     cessation
    0.38
    duled
    0.37
     commenced
    0.36
     permitió
    0.36
     polypropylene
    0.36
     discontinuation
    0.36
    Activations Density 0.016%

    No Known Activations