© 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. 15168
    Prev
    Next
    INDEX
    Explanations

    Example

    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
    翃
    -2.31
     réalisés
    -2.11
    ꜆
    -2.08
     può
    -2.06
    粜
    -2.02
    ("");
    -2.00
    ︕
    -1.97
     The
    -1.95
    他就
    -1.94
    新款
    -1.94
    POSITIVE LOGITS
    尛
    2.80
    .
    2.30
    沇
    2.25
    ྜ
    2.22
    ጺ
    2.20
    觏
    2.19
    :
    2.19
     információ
    2.17
    勍
    2.13
    乆
    2.05
    Activations Density 0.010%

    No Known Activations