© 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-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 15594
    Prev
    Next
    INDEX
    Explanations

    negative events and outcomes

    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
     peculiarities
    0.51
    здат
    0.51
    upaten
    0.51
     delinqu
    0.51
    તિહાસ
    0.51
     împre
    0.51
     formalities
    0.50
    馕
    0.50
     deficiencies
    0.50
    ؓ
    0.49
    POSITIVE LOGITS
     Limit
    0.63
     Arch
    0.61
     Egg
    0.60
     hedging
    0.59
     dec
    0.55
     ik
    0.54
     choc
    0.54
     Struggle
    0.53
     Deep
    0.53
     limiting
    0.53
    Activations Density 0.000%

    No Known Activations