© 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. 95576
    Prev
    Next
    INDEX
    Explanations

    Sunset Blvd

    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
     Bakter
    -1.21
    vejte
    -1.20
     gehouden
    -1.18
    İM
    -1.14
     apreci
    -1.12
     anvä
    -1.04
    positie
    -1.04
     meiner
    -1.04
     silnika
    -1.04
    OLAS
    -1.03
    POSITIVE LOGITS
     of
    1.20
     meninos
    1.05
     proposte
    1.04
     cioè
    1.03
    INSEE
    1.02
    終於
    1.02
     istruzioni
    1.02
     dacă
    1.01
     zugel
    1.00
    不但
    0.98
    Activations Density 0.000%

    No Known Activations