© 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. 34558
    Prev
    Next
    INDEX
    Explanations

    IC related acronyms and initialisms

    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
    山頂
    -0.75
     halfway
    -0.73
    tigma
    -0.73
     acceso
    -0.69
    wire
    -0.69
    本線
    -0.69
    手に
    -0.69
     _____
    -0.68
     DETAILS
    -0.68
     Portuguese
    -0.68
    POSITIVE LOGITS
     IC
    1.51
    IC
    1.23
     Ic
    1.11
     ic
    1.09
    ICI
    1.00
     ICF
    0.96
    ICAS
    0.91
    ici
    0.91
     ICM
    0.89
     ICH
    0.88
    Activations Density 0.046%

    No Known Activations