© 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. 12-GEMMASCOPE-2-RES-16K
    7. 15026
    Prev
    Next
    INDEX
    Explanations

    storage devices

    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_12_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
     Хабаровского
    1.02
    ത്തിലുള്ള
    0.87
    дің
    0.87
    etsk
    0.83
     polytopes
    0.82
    铊
    0.82
     tariffs
    0.82
    etsa
    0.82
    ედერ
    0.81
     পক্ষের
    0.80
    POSITIVE LOGITS
     wiped
    0.91
     δεν
    0.90
     vagina
    0.90
    ؟.
    0.90
     nessuno
    0.89
    ドライブ
    0.89
     amazingly
    0.87
     insane
    0.86
     oscura
    0.85
    ق
    0.85
    Activations Density 0.378%

    No Known Activations