© 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. 157886
    Prev
    Next
    INDEX
    Explanations

    delivery, service, prayers, rights, ordering refund

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

    dual data centers

    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
    ቸውን
    0.53
    ина
    0.48
    ır
    0.47
     attenuated
    0.47
     прибы
    0.46
     retorn
    0.46
    обы
    0.45
     확
    0.45
    inning
    0.45
    ид
    0.45
    POSITIVE LOGITS
     ಹೇ
    0.45
     Soils
    0.44
    اعر
    0.42
     Compound
    0.41
    AMIN
    0.41
    TEXT
    0.41
     branded
    0.41
     Oxidation
    0.41
     Compounds
    0.40
     FormControl
    0.40
    Activations Density 0.000%

    No Known Activations