© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 172142
    Prev
    Next
    INDEX
    Explanations

    special phrases after punctuation

    np_acts-logits-general · gemini-2.5-flash-lite

    understanding your program goals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     свет
    0.64
     маник
    0.56
    ᕇ
    0.53
     расту
    0.52
    𝘇
    0.52
    явление
    0.52
     econômica
    0.52
     означает
    0.51
    𝒓
    0.51
     растения
    0.51
    POSITIVE LOGITS
     did
    0.49
     dim
    0.45
     lo
    0.44
     ban
    0.44
     ros
    0.44
     mul
    0.43
    apa
    0.42
     Mur
    0.42
     jin
    0.42
    ahoo
    0.41
    Activations Density 0.001%

    No Known Activations