© 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. 12590
    Prev
    Next
    INDEX
    Explanations

    possessive skills or knowledge

    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
    hyst
    1.79
    las
    1.71
    h
    1.63
    wedd
    1.59
    휀
    1.59
    SUV
    1.49
    Lights
    1.49
    lub
    1.46
    bo
    1.45
    hdf
    1.43
    POSITIVE LOGITS
     endExpNow
    2.33
     компьютера
    2.04
     desktops
    2.02
    たちの
    2.02
     neurons
    2.01
     ribosome
    2.00
     сосредото
    2.00
    偣
    1.99
     cellular
    1.97
    Neurons
    1.96
    Activations Density 0.083%

    No Known Activations