© 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. 34-GEMMASCOPE-RES-131K
    7. 117819
    Prev
    Next
    INDEX
    Explanations

    no funciona

    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
     estuvieron
    -1.41
     ANCHE
    -1.14
    vermectin
    -1.09
     }));
    -1.09
     murieron
    -1.07
     soñ
    -1.05
    june
    -1.04
    愀
    -1.04
     kellett
    -1.04
     participaron
    -1.02
    POSITIVE LOGITS
     is
    1.92
     not
    1.59
     it
    1.46
     has
    1.30
     never
    1.27
     was
    1.26
     always
    1.25
     се
    1.19
     already
    1.18
     still
    1.17
    Activations Density 0.019%

    No Known Activations