© 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. 64256
    Prev
    Next
    INDEX
    Explanations

    git diff index

    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
     äldre
    -1.11
    Ї
    -1.03
    wię
    -1.03
     devlet
    -1.01
     ändå
    -1.00
     skrev
    -1.00
     stik
    -1.00
     或
    -0.99
     SISTEMA
    -0.98
     gjorde
    -0.98
    POSITIVE LOGITS
     continually
    1.26
    INFO
    1.16
     extremely
    1.09
     immense
    1.05
     decidedly
    1.03
    Inclu
    1.03
     exceedingly
    1.01
     exceptionally
    0.98
     dee
    0.97
     somewhat
    0.96
    Activations Density 0.001%

    No Known Activations