© 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. 34-GEMMASCOPE-RES-131K
    4. 60079
    Prev
    Next
    INDEX
    Explanations

    here and there

    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_34/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
    ensitive
    -0.98
    奁
    -0.86
    chuhe
    -0.85
    かなぁ
    -0.84
    っかり
    -0.84
     deſ
    -0.84
    鉨
    -0.80
    ු
    -0.80
     descendre
    -0.79
    🛏
    -0.79
    POSITIVE LOGITS
     there
    2.14
     here
    1.52
     at
    1.24
     in
    1.23
     near
    1.16
    There
    1.16
     by
    1.16
    there
    1.13
     yonder
    1.09
     where
    1.04
    Activations Density 0.014%

    No Known Activations