© 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. 118275
    Prev
    Next
    INDEX
    Explanations

    to make, to ensure, to see

    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
    tiveness
    -0.81
    &__
    -0.81
    ala
    -0.80
     verkaufen
    -0.77
    frase
    -0.76
     Gewebe
    -0.76
    מע
    -0.76
    𝟐
    -0.75
    ่ะ
    -0.75
     @"";
    -0.74
    POSITIVE LOGITS
     make
    5.59
    Make
    3.94
    make
    3.77
     Make
    3.72
     ensure
    3.34
     makes
    3.23
     MAKE
    2.77
    MAKE
    2.69
     Ensure
    2.44
    Ensure
    2.33
    Activations Density 0.117%

    No Known Activations