© 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
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 5298
    Prev
    Next
    INDEX
    Explanations

    stay + positive descriptive word

    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_262k_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
     applic
    2.13
     bushels
    1.86
     appellants
    1.83
    Ɵ
    1.81
     ascertained
    1.80
    ﺐ
    1.79
    ara
    1.77
     megawatts
    1.77
     internationaux
    1.74
     aquifers
    1.73
    POSITIVE LOGITS
    ות
    2.48
    tained
    2.17
    ка
    2.13
    ل
    2.11
    t
    2.08
    tier
    2.06
    ك
    2.05
    tır
    2.03
    ил
    1.95
    taught
    1.93
    Activations Density 0.032%

    No Known Activations