© 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. 54751
    Prev
    Next
    INDEX
    Explanations

    anything available or non-flammable

    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
    ،
    0.53
     CAUSED
    0.47
     feel
    0.45
     tung
    0.45
    ፣
    0.45
     colesterol
    0.44
    獧
    0.44
     microcos
    0.43
     regras
    0.43
    larınız
    0.43
    POSITIVE LOGITS
    ጥነት
    0.59
     Boston
    0.42
    ла
    0.42
    visitor
    0.40
    0
    0.39
     Deutschen
    0.37
     Tid
    0.37
     Internation
    0.37
     American
    0.36
    service
    0.36
    Activations Density 0.001%

    No Known Activations