© 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. 188536
    Prev
    Next
    INDEX
    Explanations

    civil engineer

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

    Josephus problem

    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
    iscilla
    0.45
    ijuana
    0.45
    ək
    0.44
    rikes
    0.44
    getCount
    0.44
    ackets
    0.43
     ක්‍ර
    0.43
    衡
    0.43
    anh
    0.42
    aterina
    0.42
    POSITIVE LOGITS
     ISM
    0.47
     agar
    0.46
     Gor
    0.46
     dopp
    0.46
     stepper
    0.45
     VU
    0.45
    Gor
    0.44
    マス
    0.44
    窯
    0.44
     DAB
    0.44
    Activations Density 0.000%

    No Known Activations