© 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. 85990
    Prev
    Next
    INDEX
    Explanations

    Remembrance and thereof

    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
    x
    -3.25
    \
    -2.72
    ]
    -2.39
    —
    -2.36
     leeren
    -2.34
     notwendigen
    -2.33
    >
    -2.23
    |
    -2.23
    !
    -2.19
    .
    -2.14
    POSITIVE LOGITS
    岽
    2.61
    ון
    2.14
    क्टर
    2.08
    很喜欢
    2.06
    罴
    2.05
    ﹶ
    2.03
    𞤤
    2.02
    ญี่ป
    2.02
    砹
    1.98
    上学
    1.94
    Activations Density 0.003%

    No Known Activations