© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 29126
    Prev
    Next
    INDEX
    Explanations

    describing the usual

    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
    なども
    -1.61
    }}{\
    -1.57
     how
    -1.52
     («
    -1.47
     deviennent
    -1.41
    </strong>
    -1.41
     semblent
    -1.39
    quatre
    -1.39
    (!__
    -1.38
    ^{(
    -1.37
    POSITIVE LOGITS
    Because
    1.82
     Because
    1.64
    ಞ
    1.58
    Where
    1.57
    ESSIONAL
    1.51
     veta
    1.42
     chiesto
    1.41
    χι
    1.41
     other
    1.40
    because
    1.40
    Activations Density 0.097%

    No Known Activations