© 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. 5823
    Prev
    Next
    INDEX
    Explanations

    reading input or prompts

    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
     numerical
    0.62
     animais
    0.62
     animals
    0.60
    動物
    0.59
     Numerical
    0.58
     animali
    0.56
     animal
    0.55
    [],
    0.55
     monkeys
    0.55
     Mathematical
    0.53
    POSITIVE LOGITS
     prompt
    0.64
    readline
    0.64
    Prompt
    0.63
    prompt
    0.58
     Prompt
    0.58
    int
    0.55
     ask
    0.54
     asked
    0.54
     chied
    0.54
     solicitar
    0.53
    Activations Density 0.136%

    No Known Activations