© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 54508
    Prev
    Next
    INDEX
    Explanations

    pronoun after punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_30_width_262k_l0_small_affine
    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
    对着
    0.37
    いない
    0.32
    lukan
    0.32
    zyst
    0.31
    ესი
    0.31
    <.
    0.31
     mediocr
    0.30
    μάτων
    0.30
    \%.
    0.30
     Viator
    0.30
    POSITIVE LOGITS
     Functional
    0.38
     integrative
    0.36
     LIKE
    0.36
     functional
    0.35
     Integrative
    0.35
     지금까지
    0.35
     zoals
    0.35
     ఇటీవల
    0.35
     embora
    0.33
     like
    0.33
    Activations Density 0.001%

    No Known Activations