© 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. 22276
    Prev
    Next
    INDEX
    Explanations

    analyze examples, construct

    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
    ना
    0.49
     daddy
    0.48
     Thought
    0.46
     miserable
    0.44
    StateToProps
    0.43
    여자
    0.42
     Daddy
    0.41
    <unused90>
    0.41
     kamp
    0.41
    𝕟
    0.40
    POSITIVE LOGITS
     четы
    0.52
    ciò
    0.51
    ė
    0.45
    orig
    0.44
    鋁
    0.43
    ătă
    0.43
    ૌ
    0.43
     ઓ
    0.42
    શ્ર
    0.42
    <0xAC>
    0.41
    Activations Density 0.000%

    No Known Activations