© 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-3-12B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 6161
    Prev
    Next
    INDEX
    Explanations

    datetime formatting or attributes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    =["
    0.56
     Rios
    0.56
     viya
    0.54
    すら
    0.51
     utilis
    0.51
     yol
    0.51
     stem
    0.50
     जबकि
    0.50
     markers
    0.49
    Dias
    0.49
    POSITIVE LOGITS
    getattr
    0.96
     getattr
    0.79
     Attribute
    0.78
    Attribute
    0.77
    属
    0.73
    屬
    0.67
     attribute
    0.65
    attribute
    0.64
     Attributes
    0.63
     attributes
    0.62
    Activations Density 0.262%

    No Known Activations