© 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. 15-GEMMASCOPE-2-RES-16K
    7. 6621
    Prev
    Next
    INDEX
    Explanations

    a/an before important words

    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_15_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
    utations
    1.12
    разде
    1.10
    ilipp
    1.10
     ама
    1.09
    壬
    1.07
    үй
    1.06
    enseit
    1.04
     penultimate
    1.03
     كلا
    1.03
    総
    1.02
    POSITIVE LOGITS
    jectories
    1.84
    年には
    1.81
     alvo
    1.75
    wpt
    1.70
    晫
    1.64
     Targets
    1.63
     Plugging
    1.63
     videolar
    1.63
     testigos
    1.62
     inci
    1.62
    Activations Density 0.145%

    No Known Activations