© 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. 1881
    Prev
    Next
    INDEX
    Explanations

    code followed by punctuation

    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
     so
    -1.47
     поэтому
    -1.21
    所以
    -1.13
    entukan
    -1.02
     Beide
    -1.02
     zarówno
    -0.99
     not
    -0.96
    ฑ
    -0.95
     both
    -0.95
    ֹא
    -0.95
    POSITIVE LOGITS
     but
    1.27
     ਵਿੱਚ
    0.98
    ͏
    0.96
    ut
    0.94
    VisualStyle
    0.93
    ívar
    0.90
    vokat
    0.89
    bolts
    0.88
    risation
    0.88
    になりますが
    0.86
    Activations Density 0.020%

    No Known Activations