© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 112691
    Prev
    Next
    INDEX
    Explanations

    making promises

    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
     \
    -2.16
    ⼥
    -2.08
     hermanas
    -2.08
    ╽
    -1.99
     valiente
    -1.97
    美丽的
    -1.95
     nehmen
    -1.80
     milyen
    -1.74
    ungalows
    -1.73
    𖣘
    -1.73
    POSITIVE LOGITS
    覿
    2.70
    饪
    2.31
     promised
    2.16
    歺
    2.06
    椟
    2.05
     that
    2.02
    鸸
    2.00
    我们可以
    2.00
    禤
    1.96
    腚
    1.94
    Activations Density 0.006%

    No Known Activations