© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 59585
    Prev
    Next
    INDEX
    Explanations

    zoned areas and property deeds

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    s
    -2.63
     Of
    -2.28
     Not
    -2.22
    規定
    -2.20
    Of
    -2.19
    他們
    -2.17
    g
    -2.13
     Когда
    -2.02
    Usually
    -2.02
     What
    -2.02
    POSITIVE LOGITS
    悫
    2.20
    皤
    2.06
     bús
    2.05
    釓
    2.02
    𓐍
    1.98
    }$
    1.94
     imó
    1.92
    presidente
    1.87
     flesta
    1.87
     milhares
    1.84
    Activations Density 0.001%

    No Known Activations