Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8069
    Prev
    Next
    INDEX
    Explanations

    strong urge or compulsion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    },[])
    -0.89
    ortunadamente
    -0.81
    iniques
    -0.75
    実は
    -0.73
     tactic
    -0.71
    taje
    -0.69
     любят
    -0.69
    maki
    -0.68
    λίου
    -0.68
    cji
    -0.68
    POSITIVE LOGITS
     compelled
    3.41
     urge
    2.84
     compulsion
    2.80
     impulse
    2.63
     compels
    2.56
     compel
    2.39
     urges
    2.11
     impulso
    2.08
     impelled
    2.03
     impulses
    2.00
    Activations Density 0.045%

    No Known Activations