© 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. 63780
    Prev
    Next
    INDEX
    Explanations

    describing places like

    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
    locator
    -0.89
    一听
    -0.83
    グルメ
    -0.82
    textStyle
    -0.81
     krás
    -0.81
     desierto
    -0.81
    VIAF
    -0.81
    rogenic
    -0.80
     profiter
    -0.80
    イビー
    -0.79
    POSITIVE LOGITS
     Europe
    1.16
     elsewhere
    1.09
     European
    1.02
     Hogwarts
    0.96
     Cheers
    0.94
     berada
    0.87
     Elsewhere
    0.85
     Africa
    0.84
    Cheers
    0.84
     another
    0.84
    Activations Density 0.033%

    No Known Activations