© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 27047
    Prev
    Next
    INDEX
    Explanations

    consequences and improvements

    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
     parfois
    -1.41
     vraiment
    -1.31
     quelquefois
    -1.30
     maintenant
    -1.30
     flera
    -1.29
     depuis
    -1.24
     bazen
    -1.22
     tambi
    -1.16
     klim
    -1.16
     sometimes
    -1.16
    POSITIVE LOGITS
     be
    2.45
     if
    2.30
     soon
    2.02
     likely
    1.55
     hopefully
    1.55
    hopefully
    1.47
     upcoming
    1.36
     tomorrow
    1.35
     nantinya
    1.33
    likely
    1.30
    Activations Density 0.342%

    No Known Activations