© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 11455
    Prev
    Next
    INDEX
    Explanations

    conjunctions and contrastive phrasing

    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
    ካት
    0.55
    替换
    0.50
    менова
    0.46
    ཟ
    0.46
     belated
    0.45
    ވި
    0.45
    超越
    0.44
    LowerCase
    0.42
    ཐ
    0.42
    Messaging
    0.42
    POSITIVE LOGITS
     This
    0.56
     these
    0.56
     These
    0.54
     this
    0.54
     একটী
    0.53
     mnoh
    0.52
     niemals
    0.52
     seldom
    0.51
     Jeżeli
    0.51
     Therefore
    0.50
    Activations Density 0.005%

    No Known Activations