© 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. 48945
    Prev
    Next
    INDEX
    Explanations

    technical identifiers and versions

    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
     custos
    0.41
    方針
    0.40
    蚁
    0.38
    -------*/
    0.38
     फ्लो
    0.38
     Oxford
    0.38
     limestone
    0.38
     ruby
    0.37
     Oxfordshire
    0.37
    尭
    0.37
    POSITIVE LOGITS
    Syn
    0.54
     syn
    0.48
     Syn
    0.47
     DSM
    0.45
    Transmission
    0.45
    Authorized
    0.43
    syn
    0.42
     Transmission
    0.42
    DSM
    0.42
    閻
    0.41
    Activations Density 0.030%

    No Known Activations