© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 42050
    Prev
    Next
    INDEX
    Explanations

    less than or under

    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
     Eine
    -1.68
     Before
    -1.59
    </b>
    -1.59
     …
    -1.52
     When
    -1.44
     $\
    -1.37
     
    -1.34
     Taking
    -1.34
     Through
    -1.33
     Creating
    -1.32
    POSITIVE LOGITS
    prende
    1.66
     jogja
    1.65
     miljoner
    1.63
    ﹕
    1.59
     leſs
    1.59
     メニュー
    1.59
    :(
    1.55
     kebaya
    1.54
    er
    1.53
     yako
    1.53
    Activations Density 0.018%

    No Known Activations