© 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. 75570
    Prev
    Next
    INDEX
    Explanations

    gaining popularity or traction

    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
    ്ല
    0.54
     całej
    0.50
    ර
    0.48
    சிரியர்
    0.48
     entier
    0.47
     geheel
    0.47
    饮料
    0.46
    珐
    0.46
     உலகின்
    0.46
     বিটিআই
    0.46
    POSITIVE LOGITS
    izó
    0.42
     propagated
    0.41
     lately
    0.40
     था
    0.39
     Lately
    0.39
     sama
    0.39
    izou
    0.39
     interesados
    0.39
     yesterday
    0.38
    0.38
    Activations Density 0.029%

    No Known Activations