© 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. 5640
    Prev
    Next
    INDEX
    Explanations

    influence how AIfearing it woulddelay purchases expectinglimit trade. They'reCareful Usage: $300

    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
    Whilst
    0.84
    ُل
    0.82
    FundMe
    0.79
    🤦
    0.79
    Fuck
    0.77
     estremamente
    0.76
    🥺
    0.76
    ⺠
    0.75
    ◯
    0.75
     wundersch
    0.75
    POSITIVE LOGITS
     takers
    0.70
     खास
    0.67
    <unused2169>
    0.66
     ills
    0.65
     bargains
    0.65
     inroads
    0.63
     chips
    0.63
     someday
    0.63
     mingling
    0.63
     foes
    0.62
    Activations Density 0.064%

    No Known Activations