© 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. 68087
    Prev
    Next
    INDEX
    Explanations

    list items following tokens like obj, i, Child, Outer, last, Today, El, Q, Ś

    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
    ема
    -0.91
     Já
    -0.91
     Sohn
    -0.85
    새
    -0.84
     able
    -0.83
    IFORN
    -0.83
    场比赛
    -0.82
     forsk
    -0.82
    shield
    -0.81
    carbons
    -0.80
    POSITIVE LOGITS
     other
    1.24
     aufgrund
    0.89
     this
    0.89
    נחנו
    0.89
     another
    0.88
     others
    0.88
     jälkeen
    0.85
     hinsichtlich
    0.84
     discussion
    0.84
    形势
    0.84
    Activations Density 0.002%

    No Known Activations