© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 12319
    Prev
    Next
    INDEX
    Explanations

    sec^2(\theta)

    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
     justifiable
    2.62
    PointerException
    2.55
    ото
    2.52
    strument
    2.52
     Brasileiro
    2.49
     noe
    2.48
     себя
    2.46
    ︎
    2.43
     Yatha
    2.42
    ীষ
    2.39
    POSITIVE LOGITS
    des
    2.62
    Des
    2.52
    ἱ
    2.50
    lul
    2.48
    room
    2.38
    >"
    2.32
    ContextCompat
    2.28
    LoginActivity
    2.28
    scribe
    2.23
    こそ
    2.23
    Activations Density 0.001%

    No Known Activations