© 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. 49934
    Prev
    Next
    INDEX
    Explanations

    Richard followed by name

    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
     συ
    -0.79
    WSGI
    -0.77
     souten
    -0.77
    kowa
    -0.73
    </th>
    -0.72
    ="?
    -0.71
    SeekBar
    -0.71
    стно
    -0.71
     dissipation
    -0.71
     misde
    -0.70
    POSITIVE LOGITS
     specially
    0.81
     :-
    0.80
    起
    0.76
     finn
    0.75
    apper
    0.74
     rezult
    0.74
     sho
    0.73
     dibuat
    0.73
    珥
    0.72
    ::_
    0.72
    Activations Density 0.032%

    No Known Activations