© 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. 14800
    Prev
    Next
    INDEX
    Explanations

    can't

    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
    น้อย
    0.58
    handel
    0.58
    homogeneous
    0.55
    陋
    0.52
     없을
    0.50
    낯
    0.48
     overr
    0.48
    ഋ
    0.48
    Nathan
    0.46
     atypical
    0.46
    POSITIVE LOGITS
     wasted
    1.30
     unused
    1.16
    浪费
    1.12
     fruitless
    1.06
     useless
    1.05
     wasting
    1.05
     inutil
    1.04
     unimplemented
    1.02
     unfinished
    0.98
     pointless
    0.96
    Activations Density 0.344%

    No Known Activations