© 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. 40-GEMMASCOPE-2-RES-65K
    7. 39
    Prev
    Next
    INDEX
    Explanations

    connects clauses with contrast

    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
    ،
    0.29
    ，
    0.23
    、
    0.22
    Every
    0.20
     every
    0.19
    ,
    0.19
    ทุก
    0.18
     ogni
    0.17
    ፣
    0.17
     delimiters
    0.17
    POSITIVE LOGITS
    which
    0.32
     which
    0.30
    although
    0.27
     although
    0.27
     cuya
    0.26
     который
    0.26
     ktoré
    0.26
     преимущественно
    0.26
     которая
    0.26
     которые
    0.25
    Activations Density 1.361%

    No Known Activations