© 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. 22-GEMMASCOPE-RES-131K
    7. 79914
    Prev
    Next
    INDEX
    Explanations

    occur followed by prepositions

    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_22/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
    橚
    -2.83
    殽
    -2.59
    ᯾
    -2.53
    Ꭳ
    -2.42
    蔟
    -2.39
    苤
    -2.27
     afecto
    -2.22
    糶
    -2.19
     entusias
    -2.19
    現在の
    -2.16
    POSITIVE LOGITS
     in
    3.86
    </em>
    2.84
    ↵
    2.44
    瞜
    2.27
    鋆
    2.22
    pecabe
    2.16
    ஂ
    2.11
     at
    2.11
     What
    2.09
     Keeping
    2.08
    Activations Density 0.029%

    No Known Activations