© 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. 11083
    Prev
    Next
    INDEX
    Explanations

    associations between or via

    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
     has
    -1.45
     it
    -1.43
     now
    -1.41
     how
    -1.39
    pasien
    -1.38
     heading
    -1.35
     ausdrück
    -1.33
     اللجنة
    -1.33
     finding
    -1.32
    ൻ
    -1.32
    POSITIVE LOGITS
     fenti
    1.51
    大概是
    1.41
    among
    1.29
     étroite
    1.27
    artiste
    1.27
    以上です
    1.27
     météo
    1.26
    earned
    1.20
    じゃあ
    1.20
     battre
    1.19
    Activations Density 0.503%

    No Known Activations