© 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-65K
    7. 45345
    Prev
    Next
    INDEX
    Explanations

    focus on specific actions

    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_65k_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
     apprehend
    0.49
     obsolete
    0.48
    ﻄ
    0.48
     malignancy
    0.47
     taint
    0.46
     kho
    0.45
     स्वतः
    0.45
     cloro
    0.45
     hydrochloric
    0.44
     scanner
    0.43
    POSITIVE LOGITS
    εργ
    0.50
    🌓
    0.44
    <0xAB>
    0.44
    饪
    0.44
     बैचलर्स
    0.43
    γκ
    0.43
    <0x9A>
    0.42
    чет
    0.42
    ig
    0.42
    স্পতি
    0.42
    Activations Density 0.002%

    No Known Activations