© 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. 1305
    Prev
    Next
    INDEX
    Explanations

    bereaved or deprived states

    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
    </i>
    -3.11
    c
    -2.91
     '
    -2.78
    an
    -2.58
    </h1>
    -2.58
    釭
    -2.53
    re
    -2.47
    </h3>
    -2.47
    1
    -2.45
    """
    -2.39
    POSITIVE LOGITS
    馓
    2.58
    驁
    2.50
    𞤢
    2.38
     dettagli
    2.36
    腚
    2.33
    鉻
    2.27
     affari
    2.19
     reconocido
    2.19
    沅
    2.16
    愎
    2.16
    Activations Density 0.003%

    No Known Activations