© 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. 75344
    Prev
    Next
    INDEX
    Explanations

    irrelevant or no bearing

    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
    की
    0.49
    ית
    0.47
    yl
    0.45
    ancient
    0.44
    كي
    0.44
     تجاوز
    0.44
    ود
    0.44
    埥
    0.43
    েল
    0.43
    ות
    0.43
    POSITIVE LOGITS
     tomatoes
    0.46
     carboxyl
    0.45
     leaflet
    0.44
     centroids
    0.44
     suitability
    0.43
     Tomatoes
    0.43
     door
    0.42
     demanda
    0.42
     pulmonary
    0.42
    </h2>
    0.41
    Activations Density 0.008%

    No Known Activations