© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 15956
    Prev
    Next
    INDEX
    Explanations

    eidolon

    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
     OFFICE
    0.24
     directora
    0.24
    Ŏ
    0.23
     proyecto
    0.22
    Partner
    0.22
    Associate
    0.21
     Partnerships
    0.21
     সহায়
    0.21
    祜
    0.21
     proyek
    0.21
    POSITIVE LOGITS
     Kanye
    0.24
     fucking
    0.23
     frenzy
    0.22
     cannibal
    0.22
     Rihanna
    0.22
     Netflix
    0.22
     freaking
    0.22
     scum
    0.22
     Eminem
    0.22
     notoriously
    0.22
    Activations Density 0.049%

    No Known Activations