© 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. 130943
    Prev
    Next
    INDEX
    Explanations

    invites, invitation, invitational, inviting

    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
    2
    -2.72
     \
    -2.63
    K
    -2.45
    S
    -2.34
    '
    -2.28
    D
    -2.27
    H
    -2.20
     pequeña
    -2.16
    </td>
    -2.14
    C
    -2.09
    POSITIVE LOGITS
    镡
    2.70
     soportar
    2.61
     Both
    2.53
    瓛
    2.50
     Then
    2.31
     rafra
    2.28
    ского
    2.23
    渼
    2.22
     réinitial
    2.19
    ный
    2.09
    Activations Density 0.005%

    No Known Activations