© 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
    2. Gemma-3-1B
    3. 7-GEMMASCOPE-2-RES-16K
    4. 1561
    Prev
    Next
    INDEX
    Explanations

    treatment and therapy regimens

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_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
     EN
    2.93
     SE
    2.48
     EAS
    2.21
     ENO
    2.18
    jPanel
    2.12
     central
    2.11
    pictureBox
    2.10
    椇
    2.10
     APPE
    2.07
    </a>
    2.04
    POSITIVE LOGITS
    awake
    2.64
    ⃛
    2.49
    ífico
    2.34
    লিত
    2.33
    legt
    2.33
    ülete
    2.30
    ownie
    2.30
     passionately
    2.27
     kepentingan
    2.24
    使う
    2.22
    Activations Density 0.471%

    No Known Activations