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. 55
    Prev
    Next
    INDEX
    Explanations

    cannabis strains

    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
     effects
    -0.96
    vistar
    -0.92
     Effects
    -0.90
     EFFECTS
    -0.87
     dis
    -0.79
    藕
    -0.79
     FX
    -0.79
    риф
    -0.75
    cjs
    -0.74
    goire
    -0.73
    POSITIVE LOGITS
     strains
    1.11
    wreck
    1.09
     Mazar
    0.94
     strain
    0.91
     Durban
    0.88
     zape
    0.85
     Krum
    0.84
     Strains
    0.83
     $\#
    0.82
    strains
    0.82
    Activations Density 0.016%

    No Known Activations