© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-65K
    7. 5960
    Prev
    Next
    INDEX
    Explanations

    educational qualifications or fields

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_width_65k_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
     competenze
    0.80
    Skill
    0.77
     conoscenze
    0.77
     cuma
    0.76
    expertise
    0.76
     både
    0.75
    💅
    0.75
    技能
    0.75
     expertise
    0.75
    ക്കിയത്
    0.74
    POSITIVE LOGITS
     Preferably
    1.18
     preferably
    1.14
    もしくは
    1.11
    preferably
    1.08
     relevant
    1.08
     preferred
    1.04
     preferable
    1.02
    कोई
    1.01
     relevante
    1.01
     any
    1.00
    Activations Density 0.068%

    No Known Activations