© 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. 14907
    Prev
    Next
    INDEX
    Explanations

    conditions for exceptions

    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
    𝓮
    2.89
    ियोजना
    2.58
    coding
    2.52
    𝙧
    2.51
    𝗼
    2.49
    ান
    2.46
    erequisite
    2.45
    ോളിക
    2.44
    <iframe>
    2.38
     rospy
    2.38
    POSITIVE LOGITS
    (
    2.08
    sworth
    1.95
    郁
    1.90
    hausen
    1.87
    )
    1.84
    weiser
    1.82
    ]^
    1.81
    =(-
    1.80
    downs
    1.80
     angel
    1.77
    Activations Density 0.006%

    No Known Activations