© 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. 2292
    Prev
    Next
    INDEX
    Explanations

    introduces what is denoted by or as

    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
    Bil
    1.55
    BIL
    1.49
     quindi
    1.48
    Limite
    1.47
    ashington
    1.46
     mécanismes
    1.46
    堬
    1.46
    Ǥ
    1.46
    Ava
    1.45
     grazie
    1.45
    POSITIVE LOGITS
     ostensibly
    1.50
     admittedly
    1.35
     seemingly
    1.28
     seeming
    1.20
     myriad
    1.18
     improbable
    1.17
     lucrative
    1.15
     certain
    1.14
     sporadic
    1.13
     some
    1.11
    Activations Density 0.666%

    No Known Activations