© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 66501
    Prev
    Next
    INDEX
    Explanations

    vanguard, head, ground, advocate

    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
    1
    -3.83
    2
    -3.09
    3
    -3.05
    \
    -2.66
    9
    -2.58
    6
    -2.41
    that
    -2.36
     substandard
    -2.33
     δύο
    -2.33
    หรือ
    -2.33
    POSITIVE LOGITS
     of
    3.05
    獁
    2.56
    ᯾
    2.56
    ꠥ
    2.55
    
    2.52
    品の
    2.50
    ”،
    2.44
    𓆜
    2.36
    鲽
    2.34
    naments
    2.27
    Activations Density 0.001%

    No Known Activations