© 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. 22-GEMMASCOPE-RES-131K
    7. 70881
    Prev
    Next
    INDEX
    Explanations

    Apache, ODI, Copyright, inhibition

    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_22/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
     Maurer
    -0.98
    |
    -0.93
     Polizei
    -0.82
    Manufacturer
    -0.82
    д
    -0.82
    並不是
    -0.81
    Maur
    -0.81
     фору
    -0.81
     recent
    -0.80
    ]
    -0.79
    POSITIVE LOGITS
     daugiau
    0.93
     its
    0.92
    точный
    0.92
     Dibu
    0.91
     amt
    0.87
    typeout
    0.84
    alou
    0.84
    тивен
    0.84
    CGRectMake
    0.83
     darbo
    0.83
    Activations Density 0.008%

    No Known Activations