© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 585
    Prev
    Next
    INDEX
    Explanations

    conjunctions and lists

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

    and followed by consequence

    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
     आणि
    0.25
     和
    0.22
     மற்றும்
    0.22
     және
    0.22
     及
    0.21
     auffi
    0.21
    ونکہ
    0.20
     হলাম
    0.20
    及び
    0.20
     و
    0.20
    POSITIVE LOGITS
     there
    0.20
    there
    0.19
     прове
    0.19
     treated
    0.18
    become
    0.18
    ier
    0.18
    ிருக்கு
    0.18
    almost
    0.18
    abis
    0.18
    rog
    0.17
    Activations Density 0.853%

    No Known Activations