© 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. 22-GEMMASCOPE-RES-131K
    7. 129419
    Prev
    Next
    INDEX
    Explanations

    unistd. include statements

    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
    '
    -1.66
     our
    -1.27
     venga
    -1.27
     우리
    -1.20
     something
    -1.20
     subjected
    -1.20
     we
    -1.19
    とい
    -1.16
     become
    -1.14
     estiver
    -1.14
    POSITIVE LOGITS
    donde
    1.41
    dersfield
    1.38
    寞
    1.31
    ());
    1.30
    пр
    1.24
    ів
    1.23
     decadent
    1.23
    monds
    1.23
    []
    1.21
    SpringBootTest
    1.20
    Activations Density 0.004%

    No Known Activations