© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 130506
    Prev
    Next
    INDEX
    Explanations

    removal processes

    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
    -4.88
    O
    -3.80
    V
    -3.78
    E
    -3.63
    (
    -3.47
    #
    -3.47
    ]
    -3.34
    C
    -3.34
    A
    -3.31
    {
    -3.30
    POSITIVE LOGITS
    趼
    3.30
    ⽌
    3.05
    慊
    2.97
    驺
    2.97
    ญี่ป
    2.97
    नलोड
    2.95
    งิน
    2.94
    CurtirCurtir
    2.91
    蘩
    2.91
    鰾
    2.83
    Activations Density 0.023%

    No Known Activations