© 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. 864
    Prev
    Next
    INDEX
    Explanations

    sincere apologies

    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
     supposed
    1.53
     head
    1.53
     governor
    1.52
    head
    1.44
     purchased
    1.43
    g
    1.41
     created
    1.40
     pushed
    1.39
     violated
    1.38
     bought
    1.38
    POSITIVE LOGITS
    <bos>
    2.06
    าลัย
    1.99
     NotImplemented
    1.88
    टकों
    1.87
    enhuma
    1.83
     nhiêu
    1.83
    ণীর
    1.81
    वीण
    1.81
    ধবার
    1.80
    امہ
    1.76
    Activations Density 0.004%

    No Known Activations