© 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. 203465
    Prev
    Next
    INDEX
    Explanations

    civic information and official/public matters

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

    public, proposal, validity

    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
    た
    0.49
     REACTORS
    0.48
    nonpayable
    0.44
     pept
    0.43
    िकुलम
    0.42
     kaleidos
    0.41
    らせ
    0.41
    響
    0.41
     solub
    0.40
    δρο
    0.40
    POSITIVE LOGITS
     नागरिक
    0.50
     নাগরিক
    0.49
     публі
    0.49
     публи
    0.48
     Zusch
    0.48
     öffentlich
    0.48
     ก
    0.47
     Catholics
    0.46
     Proposal
    0.46
     vilken
    0.46
    Activations Density 0.000%

    No Known Activations