© 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. 66123
    Prev
    Next
    INDEX
    Explanations

    specific sequence patterns

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

    cobot, tiles, system, isComposite

    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
    p
    0.51
     meditations
    0.49
     cilia
    0.46
     times
    0.45
     feedings
    0.45
     memberships
    0.45
     hairstyles
    0.44
     vegan
    0.44
     genomes
    0.43
     meditation
    0.43
    POSITIVE LOGITS
    AKER
    0.52
     Интер
    0.50
    akap
    0.49
     esimerkiksi
    0.47
    咟
    0.46
    isComposite
    0.46
    يرو
    0.46
    ScriptInterface
    0.45
    raž
    0.45
     McColl
    0.44
    Activations Density 0.001%

    No Known Activations