© 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. 225155
    Prev
    Next
    INDEX
    Explanations

    types of spending and classification

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

    nn.Linear(

    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
     朱
    0.43
     assail
    0.42
     หม
    0.42
    只见
    0.42
     ശു
    0.40
    olome
    0.39
     Resume
    0.38
     ตา
    0.38
     Repeating
    0.38
     张
    0.38
    POSITIVE LOGITS
     transitioned
    0.55
     कर्ज
    0.49
     transitioning
    0.47
    大きい
    0.47
     loans
    0.46
    Loans
    0.46
    Combin
    0.46
    Ɖ
    0.46
    উল্লেখ
    0.46
    כל
    0.45
    Activations Density 0.001%

    No Known Activations