© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 40270
    Prev
    Next
    INDEX
    Explanations

    physics experiments

    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
     saca
    -1.34
    .”
    -1.29
     perdido
    -1.20
    “
    -1.15
     baratas
    -1.15
     jardin
    -1.13
    していない
    -1.13
    !
    -1.11
     cerrado
    -1.11
     Makes
    -1.11
    POSITIVE LOGITS
    ఁ
    1.16
     posiblemente
    1.13
    ὸς
    1.13
     helyzet
    1.12
    ientras
    1.12
    嘚
    1.09
     insides
    1.07
    lysm
    1.07
    espoir
    1.06
    薗
    1.06
    Activations Density 0.000%

    No Known Activations