© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M
    5. 12-GEMMASCOPE-2-RES-16K
    7. 6564
    Prev
    Next
    INDEX
    Explanations

    medical-related or M-prefixed text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_12_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
     hexa
    2.03
     securely
    1.79
     hypo
    1.79
     chloride
    1.77
     cheat
    1.76
     contractual
    1.76
     ®
    1.74
    ❓
    1.74
     Credentials
    1.74
     Partie
    1.73
    POSITIVE LOGITS
    VJ
    1.20
    慟
    1.16
    v
    1.12
     Anf
    1.11
     јед
    1.06
     ensamb
    1.06
     incendio
    1.06
    stir
    1.04
    엮
    1.04
     âg
    1.03
    Activations Density 0.000%

    No Known Activations