© 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. 21065
    Prev
    Next
    INDEX
    Explanations

    com, immediately, days, not, mine

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

    prepositions after actions

    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
    을
    0.54
     اخر
    0.49
    ينية
    0.49
     ఎలా
    0.47
    으로
    0.46
     마지막
    0.46
     інших
    0.46
     nové
    0.45
    １
    0.45
     diğer
    0.45
    POSITIVE LOGITS
     philanthropic
    0.47
    uggling
    0.46
     rapp
    0.43
    phosphorylation
    0.43
     മനു
    0.40
     philanthropy
    0.40
    driven
    0.40
    cession
    0.39
    ruption
    0.39
    তিক্রম
    0.38
    Activations Density 0.000%

    No Known Activations