© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 135177
    Prev
    Next
    INDEX
    Explanations

    the workers, signs, markers, individuals

    np_acts-logits-general · gemini-2.5-flash-lite

    MetaHuman Integration and creation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ext
    0.51
    answer
    0.50
     През
    0.50
     Sent
    0.49
    写
    0.49
     İş
    0.47
     સમય
    0.47
     Answer
    0.47
     Illuminate
    0.47
    Spark
    0.47
    POSITIVE LOGITS
     acetaldehyde
    0.47
    暢
    0.45
     suffixes
    0.45
    లతో
    0.45
     endothelium
    0.44
    ichtig
    0.44
     voltak
    0.43
     malas
    0.41
     loafers
    0.41
     daisies
    0.41
    Activations Density 0.000%

    No Known Activations