© 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. 40-GEMMASCOPE-2-RES-262K
    7. 23936
    Prev
    Next
    INDEX
    Explanations

    va_ or va- words

    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_40_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
    *>
    0.45
    GLAND
    0.41
    "]))
    0.39
    መን
    0.38
     പരി
    0.38
     বিহ
    0.38
    oggia
    0.37
    ਬ
    0.37
    Adapted
    0.36
     disertai
    0.36
    POSITIVE LOGITS
     ва
    0.62
     VA
    0.54
    ва
    0.51
     IVA
    0.48
     Ва
    0.45
    VA
    0.44
    ВА
    0.44
    illant
    0.43
    Ва
    0.41
     AVA
    0.40
    Activations Density 0.010%

    No Known Activations