© 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. 34-GEMMASCOPE-RES-131K
    7. 59433
    Prev
    Next
    INDEX
    Explanations

    Inc incorporated

    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
     except
    -1.04
    except
    -0.97
    Except
    -0.94
     Except
    -0.84
     something
    -0.81
     Arquite
    -0.78
    ريط
    -0.78
     so
    -0.77
    ạy
    -0.76
    tagName
    -0.76
    POSITIVE LOGITS
     "../../
    0.87
    mustang
    0.85
    ůže
    0.85
     ares
    0.84
    presenta
    0.82
     caminhos
    0.81
    basedir
    0.81
    才有
    0.80
    urin
    0.79
     hacerte
    0.78
    Activations Density 0.001%

    No Known Activations