© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 48818
    Prev
    Next
    INDEX
    Explanations

    specific substring inclusion

    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
     berbeda
    -0.79
    ордина
    -0.73
    Affect
    -0.68
    농
    -0.68
     différent
    -0.68
     eterna
    -0.67
     immig
    -0.66
    yle
    -0.65
    Nove
    -0.65
     autoradio
    -0.64
    POSITIVE LOGITS
     substring
    2.14
    Substring
    1.73
    substring
    1.73
     keywords
    1.66
     searched
    1.57
    strstr
    1.57
     keyword
    1.55
     substr
    1.52
     string
    1.44
    assertIn
    1.44
    Activations Density 0.134%

    No Known Activations