© 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. 10852
    Prev
    Next
    INDEX
    Explanations

    suggesting or indicating findings

    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
    butuhkan
    -1.14
    anwal
    -1.13
    acaktır
    -1.00
    ('/:
    -0.99
    っていますが
    -0.98
     erwähnten
    -0.98
    ͣ
    -0.97
    הם
    -0.96
     tecnológico
    -0.92
    הס
    -0.92
    POSITIVE LOGITS
     the
    1.05
    again
    1.05
    それだけ
    1.03
    1.02
     selle
    1.02
    --
    1.02
    为了
    1.02
    atalyst
    1.00
    はこの
    0.98
    Ѓ
    0.98
    Activations Density 0.025%
    No Known Activations