© 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. 80857
    Prev
    Next
    INDEX
    Explanations

    compiler flags and library search paths

    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
     slecht
    -0.80
     selben
    -0.74
     enseña
    -0.73
    fficiencies
    -0.72
     horny
    -0.72
    を訪
    -0.72
    íu
    -0.72
     starving
    -0.71
    akuya
    -0.71
     navel
    -0.71
    POSITIVE LOGITS
     flags
    1.03
    ="-
    0.92
    extra
    0.91
    SEARCH
    0.88
     quote
    0.88
     include
    0.83
     ekstra
    0.82
     flag
    0.82
     nog
    0.81
    INC
    0.81
    Activations Density 0.105%

    No Known Activations