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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 15656
    Prev
    Next
    INDEX
    Explanations

    length, longer, adjustable

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

    stereotypes and harmful content

    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_16k_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
    Ferrari
    0.48
    ເຈ
    0.47
    𝗝
    0.46
    ੀ
    0.46
    Usuarios
    0.44
    Weapon
    0.44
    ────
    0.43
    を描
    0.43
     группу
    0.43
    唷
    0.43
    POSITIVE LOGITS
     longer
    0.52
     tubing
    0.51
     longueur
    0.50
     chines
    0.49
     keenly
    0.49
     ear
    0.48
     drugstore
    0.48
     hydrogen
    0.47
     adjustable
    0.47
     length
    0.47
    Activations Density 0.017%

    No Known Activations