© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 93044
    Prev
    Next
    INDEX
    Explanations

    identifiers and types

    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
     usually
    -1.43
     almost
    -1.34
     when
    -1.32
     another
    -1.27
     Usually
    -1.21
    Another
    -1.20
     arguably
    -1.20
     probably
    -1.20
     including
    -1.20
     while
    -1.16
    POSITIVE LOGITS
        
    1.30
       
    1.24
     tôt
    1.09
     lesquelles
    1.05
     già
    1.02
    けません
    1.02
    ہر
    0.98
     auparavant
    0.98
    事は
    0.98
    IONI
    0.97
    Activations Density 0.068%

    No Known Activations