© 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. 30411
    Prev
    Next
    INDEX
    Explanations

    Option type

    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
     chemical
    0.45
     et
    0.44
     Chemical
    0.44
     issu
    0.43
     send
    0.43
     cycl
    0.43
     credentials
    0.42
     u
    0.42
     aviation
    0.42
     coming
    0.41
    POSITIVE LOGITS
    넋
    0.46
    欢乐
    0.45
    തിൽ
    0.44
    ruzione
    0.43
    પણે
    0.43
    Oper
    0.43
    وینت
    0.43
     acquistare
    0.43
    ▔
    0.42
     différence
    0.42
    Activations Density 0.002%

    No Known Activations