© 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. 32760
    Prev
    Next
    INDEX
    Explanations

    background and related art

    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
    Generally
    -0.86
    Before
    -0.84
     pronunci
    -0.83
    Unlike
    -0.82
     LAUR
    -0.81
     Tyrol
    -0.79
     promont
    -0.78
     macrop
    -0.77
     parapet
    -0.76
    日至
    -0.76
    POSITIVE LOGITS
     nowy
    0.91
     pozna
    0.85
     jednej
    0.85
     zwier
    0.84
     Establish
    0.83
    ];
    0.83
     odkry
    0.82
     dobry
    0.81
     kuchen
    0.81
     rozum
    0.80
    Activations Density 0.000%

    No Known Activations