© 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. 177729
    Prev
    Next
    INDEX
    Explanations

    real estate showings

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

    hashtags for "woman"

    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
    nimi
    0.51
    𝗲
    0.51
    🅘
    0.51
     korist
    0.50
    نے
    0.48
    niew
    0.48
     yatha
    0.48
    ೕ
    0.47
    𝓼
    0.47
    ن
    0.46
    POSITIVE LOGITS
    Gauge
    0.47
    Impl
    0.45
    Request
    0.44
    PhoneNumber
    0.43
    包
    0.42
     immobil
    0.41
     offer
    0.41
     einzelnen
    0.41
     учреждений
    0.41
    Inventory
    0.40
    Activations Density 0.001%

    No Known Activations