© 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. 32976
    Prev
    Next
    INDEX
    Explanations

    programming file structures

    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
    ָם
    -0.85
     fairly
    -0.84
     people
    -0.84
     took
    -0.83
     had
    -0.82
    諳
    -0.81
     prominent
    -0.79
     countless
    -0.78
     galle
    -0.76
     required
    -0.76
    POSITIVE LOGITS
    роди
    1.05
    forged
    0.91
    ┬
    0.89
    delivered
    0.88
    nä
    0.87
    }^{*}
    0.85
    €“
    0.85
     trám
    0.85
     JADX
    0.84
     domu
    0.82
    Activations Density 0.000%

    No Known Activations