© 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. 48976
    Prev
    Next
    INDEX
    Explanations

    repository method names

    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
    타
    0.43
     polvo
    0.41
     mediterranean
    0.41
    pov
    0.40
     GV
    0.40
    峦
    0.38
    誢
    0.38
    蠟
    0.38
     mediterr
    0.37
     অথ
    0.37
    POSITIVE LOGITS
    findAll
    0.55
    Reference
    0.45
    findBy
    0.44
    Custom
    0.41
    getReference
    0.41
    deleteAll
    0.41
     ብዙውን
    0.40
     customarily
    0.39
    Mod
    0.39
    uestas
    0.39
    Activations Density 0.004%

    No Known Activations