© 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. 11740
    Prev
    Next
    INDEX
    Explanations

    weather event or metaphor

    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
    िक्की
    2.35
    getDay
    2.31
    েন্ড
    2.20
    elsk
    2.19
    iprocal
    2.17
    entwicklung
    2.11
    hts
    2.11
    덜
    2.08
    ital
    2.07
    
    2.06
    POSITIVE LOGITS
    troop
    3.17
    rong
    3.15
    <bos>
    3.12
     encountered
    2.93
    uacao
    2.84
     grantResults
    2.82
     {}".
    2.80
    ০
    2.76
    advert
    2.67
     "?"]
    2.64
    Activations Density 0.007%

    No Known Activations