© 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. 1925
    Prev
    Next
    INDEX
    Explanations

    digits and numerical values

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

    four

    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
     अपराधी
    0.46
     બંને
    0.42
     olmay
    0.41
    ორცი
    0.41
     Mitgl
    0.40
    囦
    0.40
    ರಳ
    0.40
    apsingToolbar
    0.40
    রাগ
    0.39
    ഭ്യാ
    0.39
    POSITIVE LOGITS
     四
    0.55
     நான்கு
    0.53
    receive
    0.48
    四
    0.48
     چهار
    0.47
     quad
    0.46
     চার
    0.46
     quartet
    0.45
    quad
    0.45
     حدود
    0.45
    Activations Density 0.016%

    No Known Activations