© 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-16K
    7. 5862
    Prev
    Next
    INDEX
    Explanations

    bolded headings and phrases

    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_16k_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
     superheroes
    0.42
     gì
    0.36
    必需
    0.35
    ބ
    0.35
     fertilizers
    0.35
    စု
    0.34
     arsen
    0.33
     succulents
    0.32
    ’),
    0.32
     superhero
    0.32
    POSITIVE LOGITS
    。(
    0.37
    ел
    0.37
    untes
    0.35
     aggravation
    0.34
     muttered
    0.34
    ausea
    0.34
    Grace
    0.34
    는
    0.34
    르는
    0.33
    strange
    0.33
    Activations Density 0.671%

    No Known Activations