© 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-65K
    7. 30986
    Prev
    Next
    INDEX
    Explanations

    different outcomes

    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
     sandal
    0.47
    вок
    0.45
     不
    0.45
     nicht
    0.44
     foreclosure
    0.43
     vecin
    0.43
    нить
    0.42
     չ
    0.42
     类
    0.42
     dung
    0.42
    POSITIVE LOGITS
    t
    0.48
    h
    0.44
    disabled
    0.44
     Considerando
    0.42
    still
    0.42
    d
    0.41
    superuser
    0.41
    saturated
    0.41
     वर्णित
    0.40
    described
    0.39
    Activations Density 0.004%

    No Known Activations