© 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. 22883
    Prev
    Next
    INDEX
    Explanations

    copper cable recycling

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

    work, physics, car, vehicle

    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
    oids
    0.50
    opa
    0.48
    ian
    0.47
    y
    0.46
    let
    0.46
    ized
    0.45
    izing
    0.44
    aph
    0.44
    umed
    0.43
    p
    0.43
    POSITIVE LOGITS
     प्रतिनिधित्व
    0.49
     신고
    0.48
     अगेन
    0.45
     تعرض
    0.44
     manifestly
    0.43
     igualmente
    0.42
     تب
    0.42
    ”।
    0.42
     دين
    0.41
     आल्सो
    0.41
    Activations Density 0.001%

    No Known Activations