© 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. 40-GEMMASCOPE-2-RES-65K
    7. 2757
    Prev
    Next
    INDEX
    Explanations

    bolded feature descriptions

    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_40_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
    ↵
    0.29
    There
    0.29
    If
    0.27
    (
    0.26
    ।
    0.26
    都
    0.26
    ,
    0.26
    Create
    0.25
     (
    0.25
    .
    0.25
    POSITIVE LOGITS
     skepticism
    0.29
    抜群
    0.29
     głównie
    0.26
     cryptic
    0.26
     gonflement
    0.26
     Почему
    0.25
     discursive
    0.25
     විශේෂ
    0.25
     inclusiv
    0.25
     demonic
    0.25
    Activations Density 2.186%

    No Known Activations