© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 51456
    Prev
    Next
    INDEX
    Explanations

    Italian financial and technical terms

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

    marker of

    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
    ActionButton
    0.47
     god
    0.45
     God
    0.44
    agod
    0.44
    god
    0.43
     رحمت
    0.43
    ibb
    0.42
     `"
    0.42
    uft
    0.42
    a
    0.42
    POSITIVE LOGITS
     almeno
    0.54
     novità
    0.50
     lze
    0.49
     realizzato
    0.49
     tedes
    0.49
     segnal
    0.49
    ধর্
    0.49
     resistenza
    0.48
    𝗻
    0.48
     svilupp
    0.48
    Activations Density 0.000%

    No Known Activations