© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 107332
    Prev
    Next
    INDEX
    Explanations

    question format or technical terms

    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
     again
    -0.76
     إب
    -0.71
     Calder
    -0.68
     krim
    -0.67
    zlich
    -0.66
     コード
    -0.66
    mountains
    -0.65
    ')->
    -0.63
     provided
    -0.63
     =~
    -0.63
    POSITIVE LOGITS
    licazione
    0.90
    
    0.90
     FUTURE
    0.89
     ditentukan
    0.85
     Wizards
    0.81
     chronicles
    0.80
     nutshell
    0.79
     spacecraft
    0.79
    enumii
    0.78
    thenes
    0.78
    Activations Density 0.001%

    No Known Activations