© 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. 74103
    Prev
    Next
    INDEX
    Explanations

    ldap, CID, melan, SSD, forestry, Cerv

    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
    u
    -3.16
    </h3>
    -2.89
    و
    -2.86
    珦
    -2.83
     Without
    -2.80
    媜
    -2.77
     If
    -2.77
     Pläne
    -2.67
     Daar
    -2.64
     Were
    -2.59
    POSITIVE LOGITS
    e
    3.77
    婊
    2.91
    锖
    2.47
    たまに
    2.45
    らなかった
    2.41
    少爷
    2.41
    ܆
    2.41
    焄
    2.41
    s
    2.39
    ⸫
    2.38
    Activations Density 0.028%

    No Known Activations