© 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. 136920
    Prev
    Next
    INDEX
    Explanations

    initial assumptions

    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
    (
    0.45
    icide
    0.43
    मी
    0.39
    utions
    0.39
     defining
    0.39
    Thy
    0.37
     Treasury
    0.37
     Medications
    0.37
    床
    0.36
    可以用
    0.36
    POSITIVE LOGITS
     når
    0.51
     ably
    0.50
     animación
    0.50
    વાલ
    0.48
     artyku
    0.48
     expliqué
    0.48
     iż
    0.47
    
    0.47
     infringe
    0.47
    гә
    0.47
    Activations Density 0.008%

    No Known Activations