© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 86163
    Prev
    Next
    INDEX
    Explanations

    organizations and communities

    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
     item
    -1.27
    ]
    -1.20
    ↵↵↵
    -1.16
    D
    -1.12
    嗮
    -1.11
    P
    -1.06
     metal
    -1.06
     organic
    -1.05
    ].
    -1.04
     которые
    -1.03
    POSITIVE LOGITS
    𖡼
    1.23
     dispen
    1.20
    
    1.19
     ""));
    1.18
    ætter
    1.17
     chrétienne
    1.16
    StateChanged
    1.15
     stanov
    1.13
    淖
    1.13
    wym
    1.13
    Activations Density 0.676%

    No Known Activations