© 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. 116534
    Prev
    Next
    INDEX
    Explanations

    delivery UPS first payment local

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

    finding explanation through lens

    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
    ঢ়
    0.51
    <0x1D>
    0.50
    fl
    0.49
     sterling
    0.48
    s
    0.48
    if
    0.46
    ɨ
    0.46
    kas
    0.46
     speichern
    0.46
    unning
    0.45
    POSITIVE LOGITS
     annihilated
    0.44
     искусства
    0.43
     amacı
    0.43
    র্ষি
    0.43
    ycznej
    0.43
     ዓ
    0.43
    പാട
    0.43
     angered
    0.42
     sufrió
    0.42
    谕
    0.42
    Activations Density 0.000%

    No Known Activations