© 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. 148868
    Prev
    Next
    INDEX
    Explanations

    all sales / completely broken

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

    weeks, salary, goal, results

    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
    นะ
    0.52
    當然
    0.51
     क्योंकि
    0.50
     Конечно
    0.48
     เพราะ
    0.48
     γιατί
    0.47
    因为
    0.47
     많
    0.47
     जरूर
    0.47
     Certainly
    0.47
    POSITIVE LOGITS
     coupled
    0.48
     experimentally
    0.43
    Adam
    0.42
     Adam
    0.40
     ostensibly
    0.40
     who
    0.39
     انج
    0.39
     آگ
    0.39
     Alison
    0.39
     B
    0.39
    Activations Density 0.005%

    No Known Activations