© 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. 63059
    Prev
    Next
    INDEX
    Explanations

    Agency or Docket followed by No

    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
    所谓
    -0.84
    къ
    -0.80
     Knowing
    -0.74
     ASME
    -0.71
     tote
    -0.71
     Perhaps
    -0.69
    ories
    -0.69
    这样的
    -0.68
     Amherst
    -0.67
    HORIZONTAL
    -0.66
    POSITIVE LOGITS
    一起去
    1.03
    Licence
    0.82
    Mord
    0.81
    holo
    0.78
    ftant
    0.76
    ัณฑ์
    0.76
    糜
    0.75
    väll
    0.74
     Libert
    0.74
    permit
    0.73
    Activations Density 0.008%

    No Known Activations