© 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. 81397
    Prev
    Next
    INDEX
    Explanations

    pepper, total, less

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

    adjust quantities, budget, activities

    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
    }||
    0.47
    |।
    0.47
     બંધ
    0.46
    ührung
    0.44
    bindingFields
    0.43
    für
    0.42
    ürk
    0.42
    qttr
    0.42
    "/"
    0.42
    <unused1049>
    0.42
    POSITIVE LOGITS
    ការ
    0.47
     overlooked
    0.42
    mol
    0.41
     atrial
    0.41
    ने
    0.40
    ey
    0.40
    Array
    0.40
    お金
    0.40
     underrated
    0.39
     are
    0.39
    Activations Density 0.001%

    No Known Activations