© 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-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-262K
    7. 146844
    Prev
    Next
    INDEX
    Explanations

    classification of metals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    繇
    0.72
    женности
    0.66
     स्तन
    0.66
    Ey
    0.65
     journalistic
    0.64
     осозна
    0.64
     aware
    0.63
     있을
    0.61
    ]['
    0.61
    ায়
    0.59
    POSITIVE LOGITS
     metals
    0.87
     materials
    0.84
     Components
    0.83
     components
    0.81
    ผลิตภัณฑ์
    0.75
    קות
    0.73
     گے
    0.73
     materiais
    0.73
     Murn
    0.73
     Materials
    0.73
    Activations Density 0.001%

    No Known Activations