© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 128698
    Prev
    Next
    INDEX
    Explanations

    what happens when/if

    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
    '
    -1.97
     implementation
    -1.59
     history
    -1.48
    ]
    -1.47
     admired
    -1.37
     development
    -1.37
     time
    -1.34
     первый
    -1.33
     accommodating
    -1.31
    鬟
    -1.31
    POSITIVE LOGITS
     you
    1.65
    簓
    1.54
    焢
    1.52
     грудня
    1.48
     incomplète
    1.45
     miten
    1.43
     ucap
    1.41
     giacca
    1.41
     occhiali
    1.41
    を読む
    1.39
    Activations Density 0.022%

    No Known Activations