© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M
    5. 12-GEMMASCOPE-2-RES-16K
    7. 7600
    Prev
    Next
    INDEX
    Explanations

    i think / i know / i'm

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_12_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
     fucking
    1.59
     shit
    1.41
    世界
    1.37
     todo
    1.37
    -
    1.35
     mundo
    1.32
    В
    1.30
    starts
    1.29
    v
    1.28
    所有的
    1.27
    POSITIVE LOGITS
     solicited
    2.00
     cancelButton
    1.98
     inquired
    1.96
     concurred
    1.96
     diskusi
    1.94
     negotiator
    1.94
     cautioned
    1.92
     remon
    1.88
     Elkus
    1.88
     contemplated
    1.88
    Activations Density 0.120%

    No Known Activations