© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 7108
    Prev
    Next
    INDEX
    Explanations

    phonetic symbols and delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    9
    0.67
    2
    0.64
    7
    0.63
    紙
    0.60
    1
    0.59
    6
    0.59
    事前に
    0.59
    4
    0.57
    8
    0.56
    మంది
    0.54
    POSITIVE LOGITS
     ellipso
    0.72
     inhom
    0.70
     uniaxial
    0.69
     corpora
    0.69
     homogene
    0.68
     polycrystalline
    0.68
     stochastic
    0.67
     GaAs
    0.66
     perturbative
    0.65
     crystalline
    0.64
    Activations Density 0.022%

    No Known Activations