© 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. 90620
    Prev
    Next
    INDEX
    Explanations

    descriptive phrases

    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
     بسیاری
    0.45
     =
    0.45
     mayor
    0.45
     +
    0.43
    町
    0.43
     &
    0.43
    ・
    0.43
    ఇ
    0.43
     دوم
    0.42
     많은
    0.42
    POSITIVE LOGITS
    ophers
    0.45
     biomark
    0.43
    providers
    0.41
     pouvaient
    0.41
     comigo
    0.41
    ເພດ
    0.41
    劷
    0.41
     employers
    0.40
    辙
    0.40
     depres
    0.40
    Activations Density 0.008%

    No Known Activations