© 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. 34-GEMMASCOPE-RES-131K
    7. 45610
    Prev
    Next
    INDEX
    Explanations

    end of clause nouns or past participles

    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
     $\&$
    -1.46
     credere
    -1.36
     (!__
    -1.21
    ﾒ
    -1.19
     guardare
    -1.17
     aspiring
    -1.16
     onore
    -1.16
     liberi
    -1.15
     другая
    -1.14
     superare
    -1.14
    POSITIVE LOGITS
     (
    2.27
    Além
    1.51
     despite
    1.33
    Apesar
    1.27
    Mesmo
    1.24
    arcoma
    1.23
     både
    1.22
     —
    1.21
     –
    1.21
     if
    1.21
    Activations Density 0.136%

    No Known Activations