© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 66906
    Prev
    Next
    INDEX
    Explanations

    peace and war parties

    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
     tiež
    -1.73
     you
    -1.72
     also
    -1.67
     también
    -1.64
     также
    -1.53
     and
    -1.49
     também
    -1.42
     including
    -1.30
     however
    -1.29
     due
    -1.27
    POSITIVE LOGITS
    hoots
    1.34
    taient
    1.32
    lllll
    1.27
    Acab
    1.26
    eping
    1.25
    ències
    1.22
    lllllll
    1.20
     bouche
    1.19
    aneity
    1.18
    llllll
    1.17
    Activations Density 0.028%

    No Known Activations