© 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. 3079
    Prev
    Next
    INDEX
    Explanations

    conjunctions like 'but' and 'or'

    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
    ،
    0.52
    ，
    0.50
    .
    0.44
    、
    0.39
    ("
    0.35
    ．
    0.32
    、「
    0.31
    "",
    0.31
     другого
    0.30
    _
    0.29
    POSITIVE LOGITS
     illetve
    0.49
     მაგრამ
    0.41
     mutta
    0.40
     اتارنا
    0.38
     lakini
    0.37
    but
    0.36
     sondern
    0.36
     maar
    0.34
     odnosno
    0.34
    n
    0.33
    Activations Density 0.506%

    No Known Activations