© 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-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 3441
    Prev
    Next
    INDEX
    Explanations

    designed for or used for

    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
    belongs
    1.70
     newest
    1.69
    んばんは
    1.68
     Belong
    1.66
     nhanh
    1.65
     Conservatory
    1.64
    éral
    1.63
    َوْ
    1.61
    ordat
    1.60
    ISTA
    1.59
    POSITIVE LOGITS
     tasked
    1.44
    用来
    1.37
     통해서
    1.18
     utilizzati
    1.16
     aimed
    1.16
     designed
    1.16
    用于
    1.15
     chargés
    1.14
     impregnated
    1.12
     utilizadas
    1.12
    Activations Density 0.343%

    No Known Activations