© 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. 73086
    Prev
    Next
    INDEX
    Explanations

    action verbs after to

    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
    žiť
    -1.65
     måneder
    -1.59
     varies
    -1.58
    (/^
    -1.51
     during
    -1.50
    大部分
    -1.47
    l
    -1.47
    入
    -1.46
    illi
    -1.46
     throughout
    -1.45
    POSITIVE LOGITS
     mensen
    1.71
    あんまり
    1.53
     beruf
    1.53
     able
    1.52
    だら
    1.46
     нового
    1.43
     triko
    1.43
    かもし
    1.41
    ごめん
    1.41
    racia
    1.40
    Activations Density 0.046%

    No Known Activations