© 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. 34-GEMMASCOPE-RES-131K
    7. 108826
    Prev
    Next
    INDEX
    Explanations

    numbers 1 to 20

    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
    Several
    -1.08
     Several
    -1.03
    sixth
    -1.02
     ketiga
    -1.01
    第四
    -0.95
     fourth
    -0.94
    fourth
    -0.94
    第五
    -0.93
     several
    -0.92
    fifth
    -0.92
    POSITIVE LOGITS
     twelve
    1.17
     douze
    1.13
     eighteen
    1.12
     twenty
    1.12
     seventy
    1.02
     nineteen
    1.02
    twelve
    1.02
     sixty
    1.01
     vingt
    0.96
     sixteen
    0.94
    Activations Density 0.146%

    No Known Activations