© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 70209
    Prev
    Next
    INDEX
    Explanations

    code and technical terms

    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
    メット
    -0.84
    ائق
    -0.79
     bancaire
    -0.77
    넬
    -0.75
     negozio
    -0.74
    Eben
    -0.73
     their
    -0.70
    styrene
    -0.69
     Моло
    -0.69
     régimen
    -0.68
    POSITIVE LOGITS
    这下
    0.89
    thentication
    0.88
    ddress
    0.85
    __()
    0.83
    essions
    0.82
    rosis
    0.81
    *.
    0.81
    hibitions
    0.81
    })
    0.80
    cist
    0.80
    Activations Density 0.008%

    No Known Activations