© 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. 585
    Prev
    Next
    INDEX
    Explanations

    scripts_ A UK Receive the The data Transmission of

    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
     DETROIT
    -0.85
     sak
    -0.84
    zdo
    -0.84
    𝒲
    -0.82
     Melton
    -0.82
    ionista
    -0.81
    𝔠
    -0.81
    ORIAL
    -0.80
     kantor
    -0.79
     onu
    -0.79
    POSITIVE LOGITS
     regress
    0.77
    Ư
    0.73
    ครับ
    0.71
    úmenes
    0.70
    olkata
    0.70
     Zurück
    0.69
    ・
    0.67
     shaded
    0.65
     miserable
    0.65
     paragraph
    0.65
    Activations Density 0.000%

    No Known Activations