© 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. 34-GEMMASCOPE-RES-131K
    7. 57135
    Prev
    Next
    INDEX
    Explanations

    neutron star

    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
     Salinity
    -0.73
     surat
    -0.66
    PENDING
    -0.66
     signes
    -0.66
     económico
    -0.65
    orgs
    -0.65
    やってきた
    -0.65
    蹤
    -0.65
    hiding
    -0.65
    ]*
    -0.64
    POSITIVE LOGITS
     Group
    0.73
    NSIndexPath
    0.68
     ISS
    0.68
    endgroup
    0.68
    anto
    0.68
    ili
    0.66
     Martial
    0.66
    è
    0.66
    erequisites
    0.66
     Report
    0.64
    Activations Density 0.053%

    No Known Activations