© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 11655
    Prev
    Next
    INDEX
    Explanations

    the or short followed by specific nouns

    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
    рата
    2.71
    elni
    2.60
    لر
    2.55
    涜
    2.42
     bela
    2.32
    髻
    2.25
    ر
    2.24
    िक
    2.22
     Tinto
    2.21
     menikah
    2.20
    POSITIVE LOGITS
    hline
    2.55
    राष्ट
    2.32
    ible
    2.30
    opher
    2.08
     Outside
    2.07
    Outside
    2.07
    outside
    2.05
     Summar
    2.04
    amyl
    2.01
    ressions
    2.00
    Activations Density 0.041%

    No Known Activations